# ProAgentStore MCP server

Agent View of the PolicyLayer registry record for ProAgentStore: identity, probed posture, risk grade, and all 243 tools classified. HTML page: https://policylayer.com/tools/io-github-proagentstore-platform

## Facts

- Server id: `https://mcp.proagentstore.online/mcp`
- Homepage: https://github.com/ProAgentStore/platform
- Registry record: grade D, identity unverified
- Lifecycle: active
- Auth posture: gated
- Rate-limited: no
- Tools: 243
- Tool categories present: Destructive, Execute, Read, Write
- Tags: io github proagentstore platform, admin, automation
- Record last modified: 2026-10-01T17:53:07.306Z

## Tools (243)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `cancel_instance_task` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/cancel-instance-task.md |
| `clear_finished_tasks` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/clear-finished-tasks.md |
| `clear_instance_messages` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/clear-instance-messages.md |
| `clear_instance_voice_settings` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/clear-instance-voice-settings.md |
| `coding_loop_queue_cancel` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-queue-cancel.md |
| `coding_repo_remove` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/coding-repo-remove.md |
| `delete_agent` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-agent.md |
| `delete_agent_knowledge` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-agent-knowledge.md |
| `delete_agent_task` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-agent-task.md |
| `delete_connection` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-connection.md |
| `delete_feedback` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-feedback.md |
| `delete_instance_connector_grant` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-connector-grant.md |
| `delete_instance_file` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-file.md |
| `delete_instance_knowledge` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-knowledge.md |
| `delete_instance_memory` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-memory.md |
| `delete_instance_message` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-message.md |
| `delete_instance_task` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-task.md |
| `delete_instance_trigger` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-instance-trigger.md |
| `delete_supervision` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/delete-supervision.md |
| `forget_runner_node` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/forget-runner-node.md |
| `remove_repo` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/remove-repo.md |
| `unregister_instance_runtime` | Destructive | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/unregister-instance-runtime.md |
| `answer_instance_input` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/answer-instance-input.md |
| `answer_instance_mcp_input_request` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/answer-instance-mcp-input-request.md |
| `apply_to_job` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/apply-to-job.md |
| `approve_instance_task` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/approve-instance-task.md |
| `call_instance_tool` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/call-instance-tool.md |
| `chat_with_agent` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/chat-with-agent.md |
| `chat_with_instance` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/chat-with-instance.md |
| `coding_engine_reauth` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-engine-reauth.md |
| `coding_loop_start` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-start.md |
| `coding_loop_stop` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-stop.md |
| `coding_overseer` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-overseer.md |
| `coding_session_end` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-end.md |
| `coding_session_fresh` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-fresh.md |
| `coding_session_open` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-open.md |
| `coding_session_restart` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-restart.md |
| `continue_instance_run` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/continue-instance-run.md |
| `end_instance_takeover` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/end-instance-takeover.md |
| `execute_agent_builder_plan` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/execute-agent-builder-plan.md |
| `force_runner_attach` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/force-runner-attach.md |
| `pause_instance` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/pause-instance.md |
| `replay_connection_delivery` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/replay-connection-delivery.md |
| `resume_instance` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/resume-instance.md |
| `resume_instance_takeover` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/resume-instance-takeover.md |
| `run_instance_task` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/run-instance-task.md |
| `run_instance_trigger` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/run-instance-trigger.md |
| `send_instance_takeover_input` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/send-instance-takeover-input.md |
| `set_instance_runner_node` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-runner-node.md |
| `start_instance_browser_task` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/start-instance-browser-task.md |
| `start_instance_loop` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/start-instance-loop.md |
| `stop_instance_loop` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/stop-instance-loop.md |
| `test_instance_mcp_server` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/test-instance-mcp-server.md |
| `trigger_agent_deploy` | Execute | High | https://policylayer.com/tools/io-github-proagentstore-platform/trigger-agent-deploy.md |
| `cancel_instance` | Financial | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/cancel-instance.md |
| `set_budget_limits` | Financial | Critical | https://policylayer.com/tools/io-github-proagentstore-platform/set-budget-limits.md |
| `name` | Other | Low | https://policylayer.com/tools/io-github-proagentstore-platform/name.md |
| `account_activity` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/account-activity.md |
| `agent_activity` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-activity.md |
| `agent_analytics` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-analytics.md |
| `agent_deploy_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-deploy-status.md |
| `agent_info` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-info.md |
| `agent_messages` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-messages.md |
| `agent_trace` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/agent-trace.md |
| `ask_ticket` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/ask-ticket.md |
| `billing_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/billing-status.md |
| `check_instance_loop` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/check-instance-loop.md |
| `coding_diagnostics` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-diagnostics.md |
| `coding_engine_get` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-engine-get.md |
| `coding_instance_deploy_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-instance-deploy-status.md |
| `coding_loop_queue` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-queue.md |
| `coding_loop_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-status.md |
| `coding_loop_trace` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-loop-trace.md |
| `coding_repos_list` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-repos-list.md |
| `coding_session_capture` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-capture.md |
| `coding_session_message` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-session-message.md |
| `coding_sessions_list` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-sessions-list.md |
| `coding_terminal` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-terminal.md |
| `coding_timeline` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/coding-timeline.md |
| `connector_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/connector-status.md |
| `email_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/email-status.md |
| `error_summary` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/error-summary.md |
| `export_agent` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/export-agent.md |
| `get_account_preferences` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-account-preferences.md |
| `get_agent_board_config` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-board-config.md |
| `get_agent_capabilities` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-capabilities.md |
| `get_agent_memory` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-memory.md |
| `get_agent_settings_schema` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-settings-schema.md |
| `get_agent_state` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-state.md |
| `get_agent_stats_schema` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-agent-stats-schema.md |
| `get_apply_tips` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-apply-tips.md |
| `get_budget_limits` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-budget-limits.md |
| `get_creator_dashboard` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-creator-dashboard.md |
| `get_instance_behaviour_schema` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-behaviour-schema.md |
| `get_instance_board_config` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-board-config.md |
| `get_instance_connection_guide` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-connection-guide.md |
| `get_instance_connector_account` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-connector-account.md |
| `get_instance_instructions` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-instructions.md |
| `get_instance_loop_limits` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-loop-limits.md |
| `get_instance_loop_presets` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-loop-presets.md |
| `get_instance_memory` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-memory.md |
| `get_instance_operator_manual` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-operator-manual.md |
| `get_instance_pipeline` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-pipeline.md |
| `get_instance_settings` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-settings.md |
| `get_instance_state` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-state.md |
| `get_instance_stats` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-stats.md |
| `get_instance_task` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-task.md |
| `get_instance_terminal_session` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-terminal-session.md |
| `get_instance_voice_settings` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-instance-voice-settings.md |
| `get_profile` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-profile.md |
| `get_translation_config` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-translation-config.md |
| `get_usage_dashboard` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/get-usage-dashboard.md |
| `grant_instance_connector_folder` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/grant-instance-connector-folder.md |
| `hint_instance_task` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/hint-instance-task.md |
| `ingest_instance_knowledge_url` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/ingest-instance-knowledge-url.md |
| `ingest_repo_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/ingest-repo-status.md |
| `instance_activity` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-activity.md |
| `instance_board` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-board.md |
| `instance_messages` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-messages.md |
| `instance_runner_node` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-runner-node.md |
| `instance_runtime_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-runtime-status.md |
| `instance_task_events` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/instance-task-events.md |
| `keys_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/keys-status.md |
| `list_agent_files` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-agent-files.md |
| `list_agent_repo_files` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-agent-repo-files.md |
| `list_agent_tasks` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-agent-tasks.md |
| `list_agents` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-agents.md |
| `list_collections` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-collections.md |
| `list_connection_deliveries` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-connection-deliveries.md |
| `list_connections` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-connections.md |
| `list_connectors` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-connectors.md |
| `list_errors` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-errors.md |
| `list_feedback` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-feedback.md |
| `list_instance_collections` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-collections.md |
| `list_instance_connector_consents` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-connector-consents.md |
| `list_instance_connector_grants` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-connector-grants.md |
| `list_instance_connectors` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-connectors.md |
| `list_instance_drive_files` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-drive-files.md |
| `list_instance_files` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-files.md |
| `list_instance_knowledge` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-knowledge.md |
| `list_instance_mcp_grants` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-mcp-grants.md |
| `list_instance_mcp_input_requests` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-mcp-input-requests.md |
| `list_instance_tools` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-tools.md |
| `list_instance_trigger_events` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-trigger-events.md |
| `list_instance_triggers` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-instance-triggers.md |
| `list_knowledge` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-knowledge.md |
| `list_mcp_presets` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-mcp-presets.md |
| `list_notifications` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-notifications.md |
| `list_pipeline_runs` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-pipeline-runs.md |
| `list_runner_nodes` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-runner-nodes.md |
| `list_stats_sources` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-stats-sources.md |
| `list_supervision` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-supervision.md |
| `list_trigger_actions` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/list-trigger-actions.md |
| `mcp_audit_log` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/mcp-audit-log.md |
| `my_agent` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/my-agent.md |
| `my_agents` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/my-agents.md |
| `my_instances` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/my-instances.md |
| `platform_guide` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/platform-guide.md |
| `platform_health` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/platform-health.md |
| `preview_instance_run_continue` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/preview-instance-run-continue.md |
| `preview_instance_trigger` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/preview-instance-trigger.md |
| `query_instance_records` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/query-instance-records.md |
| `query_records` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/query-records.md |
| `read_agent_file` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/read-agent-file.md |
| `recent_instances` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/recent-instances.md |
| `record_instance_feedback` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/record-instance-feedback.md |
| `resync_instance_personality` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/resync-instance-personality.md |
| `runner_node_forget_preflight` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/runner-node-forget-preflight.md |
| `sdk_reference` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/sdk-reference.md |
| `search_agent_knowledge` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/search-agent-knowledge.md |
| `search_instance_knowledge` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/search-instance-knowledge.md |
| `system_status` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/system-status.md |
| `ticket_thread` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/ticket-thread.md |
| `usage_summary` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/usage-summary.md |
| `vector_stats` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/vector-stats.md |
| `whoami` | Read | Low | https://policylayer.com/tools/io-github-proagentstore-platform/whoami.md |
| `add_instance_knowledge` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/add-instance-knowledge.md |
| `add_knowledge` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/add-knowledge.md |
| `apply_account_coding_default` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/apply-account-coding-default.md |
| `batch_write_agent_files` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/batch-write-agent-files.md |
| `chat_with_my_agent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/chat-with-my-agent.md |
| `coding_engine_set` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/coding-engine-set.md |
| `coding_repo_add` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/coding-repo-add.md |
| `create_agent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-agent.md |
| `create_agent_task` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-agent-task.md |
| `create_agent_version` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-agent-version.md |
| `create_collection` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-collection.md |
| `create_connection` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-connection.md |
| `create_instance_ticket` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-instance-ticket.md |
| `create_instance_trigger` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-instance-trigger.md |
| `create_supervision` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/create-supervision.md |
| `import_instance_drive_file` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/import-instance-drive-file.md |
| `import_instance_workdrive_file` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/import-instance-workdrive-file.md |
| `ingest_repo` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/ingest-repo.md |
| `insert_instance_record` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/insert-instance-record.md |
| `insert_record` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/insert-record.md |
| `mark_all_notifications_read` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/mark-all-notifications-read.md |
| `mark_notification_read` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/mark-notification-read.md |
| `plan_agent_builder` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/plan-agent-builder.md |
| `promote_board_item` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/promote-board-item.md |
| `register_instance_runtime` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/register-instance-runtime.md |
| `rename_instance` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/rename-instance.md |
| `resolve_feedback` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/resolve-feedback.md |
| `rollback_agent_version` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/rollback-agent-version.md |
| `runner_setup` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/runner-setup.md |
| `runner_update` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/runner-update.md |
| `scaffold_agent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/scaffold-agent.md |
| `set_account_preferences` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-account-preferences.md |
| `set_agent_capabilities` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-agent-capabilities.md |
| `set_agent_settings_schema` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-agent-settings-schema.md |
| `set_agent_state` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-agent-state.md |
| `set_agent_stats_schema` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-agent-stats-schema.md |
| `set_board_item_status` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-board-item-status.md |
| `set_connection_enabled` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-connection-enabled.md |
| `set_instance_board_config` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-board-config.md |
| `set_instance_connector_account` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-connector-account.md |
| `set_instance_connector_consent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-connector-consent.md |
| `set_instance_instructions` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-instructions.md |
| `set_instance_loop_limits` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-loop-limits.md |
| `set_instance_loop_presets` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-loop-presets.md |
| `set_instance_mcp_grant` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-mcp-grant.md |
| `set_instance_model` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-model.md |
| `set_instance_operator_manual` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-operator-manual.md |
| `set_instance_settings` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-settings.md |
| `set_instance_stats` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-stats.md |
| `set_instance_terminal_session` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-terminal-session.md |
| `set_instance_tool` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-tool.md |
| `set_instance_voice_settings` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-instance-voice-settings.md |
| `set_supervision_enabled` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-supervision-enabled.md |
| `set_translation_config` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/set-translation-config.md |
| `subscribe_agent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/subscribe-agent.md |
| `update_agent` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-agent.md |
| `update_agent_board_config` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-agent-board-config.md |
| `update_agent_task` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-agent-task.md |
| `update_board_ticket` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-board-ticket.md |
| `update_instance_knowledge` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-instance-knowledge.md |
| `update_instance_record` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-instance-record.md |
| `update_profile` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-profile.md |
| `update_record` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/update-record.md |
| `upload_agent_file` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/upload-agent-file.md |
| `upload_resume` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/upload-resume.md |
| `write_agent_file` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/write-agent-file.md |
| `write_instance_memory` | Write | Medium | https://policylayer.com/tools/io-github-proagentstore-platform/write-instance-memory.md |

## Tool descriptions

- `cancel_instance_task` — Cancel a task on the registered local or managed browser runtime for a private instance.
- `clear_instance_messages` — Clear a subscribed instance
- `clear_instance_voice_settings` — Drop a subscribed instance
- `coding_loop_queue_cancel` — Withdraw a queued objective before it starts. Takes the
- `coding_repo_remove` — Detach a repo from a coding instance — the counterpart to coding_repo_add, and the way to clean up a binding that was added in error or whose local checkout no longer exists. Identify the repo by
- `delete_agent` — Permanently delete one of YOUR OWN agent TEMPLATES. This also removes the creator
- `delete_agent_knowledge` — Permanently remove one knowledge document from an agent TEMPLATE. This changes what new subscribers can receive; it does not edit existing instances. Read the template
- `delete_agent_task` — Remove a standing task from an instance
- `delete_connection` — Delete an event connection for good. This destroys the edge
- `delete_feedback` — Permanently delete one feedback row — the owner
- `delete_instance_connector_grant` — Revoke an instance
- `delete_instance_file` — Delete an uploaded file from a subscribed instance (Knowledge → Files). Removes the R2 object, its metadata, and its vectors.
- `delete_instance_knowledge` — Delete a knowledge document from your private subscribed instance.
- `delete_instance_memory` — Delete one memory entry (by key) from a subscribed instance.
- `delete_instance_message` — Permanently delete the conversational turn containing one message from a subscribed instance. This can remove paired user/assistant messages and attached voice audio, but cannot unmix that turn from an existing conversation summary or ex…
- `delete_instance_task` — Delete a ticket from a private instance
- `delete_instance_trigger` — Delete a configured instance trigger. This removes its event history and connector sync ledger.
- `delete_supervision` — Remove a supervision link so the supervisor can no longer delegate to that agent. Destructive and silent: afterwards the supervisor does not error, the subordinate simply becomes unreachable to it. Dry-run it first to check the link id, …
- `forget_runner_node` — Permanently remove a disconnected machine
- `remove_repo` — Remove one indexed repository from a repo-chat instance (by repo_url or owner/repo), or all of them if neither is given. Deletes its vectors and overview.
- `unregister_instance_runtime` — Remove the registered runtime endpoint for one of your private instances.
- `answer_instance_input` — Answer a needs_input handoff: an agent paused mid-run because it needs a value it must not invent (work authorization, a notice period, an account detail), and is holding the run open waiting for it. Supply the value and the run continue…
- `answer_instance_mcp_input_request` — Answer or cancel a paused outbound MCP call.
- `apply_to_job` — Launch the LLM-driven job application for a private apply-agent instance: the PAGS agent drives the user
- `approve_instance_task` — Approve a browser runtime task waiting for human approval. Cannot approve a connector call held back by the per-call approval gate — those are approved by a person in the console, which is the whole point of that gate.
- `call_instance_tool` — Invoke a connector tool (e.g. github_workflow_runs, github_list_issues) on one of your instances. This is a two-step wrapper: first call list_instance_tools with allowed_only:true and schemas:true, find the target tool, then pass
- `chat_with_agent` — Send a message to a published agent (trial mode)
- `chat_with_instance` — Chat with your private subscribed instance of an agent. This is the real runtime path with user-owned state and credentials.
- `coding_engine_reauth` — Sign a coding engine back in from any device when it is blocked on its own login (
- `coding_loop_start` — Give an agent an objective and let it work on it autonomously, on the server. Returns a run id immediately — poll status with coding_loop_status and live work events with coding_loop_trace; the run keeps going after this call returns and…
- `coding_loop_stop` — Ask an autonomous run on an instance to stop. Cooperative: the step in flight finishes and settles its spend. Omit run_id to stop the instance
- `coding_overseer` — Ask the cross-repo Overseer agent. It sees all repos, their live sessions, and recent terminal output. Can answer questions and drive Claude Code on specific repos.
- `coding_session_end` — End a coding session completely. Stops the CLI process/session on the runner.
- `coding_session_fresh` — End the current session and start a brand new one (clean state, no --resume). Fixes corrupted CLI state.
- `coding_session_open` — Pick up work on a repo: opens its conversation and CONTINUES where the last one left off (the engine keeps the previous context for four days), which is what you want for a follow-up question or a second instruction on the same task. Say…
- `coding_session_restart` — Restart the coding CLI session on the selected runner node. Use when the CLI is stuck or erroring.
- `continue_instance_run` — Carry a STOPPED run
- `end_instance_takeover` — End a human-takeover session, handing the browser back. This does NOT resume the run — use resume_instance_takeover for that. Ending is the one takeover control whose failure is invisible from outside: if it fails the agent still holds t…
- `execute_agent_builder_plan` — Execute a reviewed agent-builder plan to create or scaffold a new agent template. This can create durable platform state and, for a scaffold plan, repository material; preview first and pass the exact confirmation only when the plan is t…
- `force_runner_attach` — Force a machine
- `pause_instance` — Temporarily stop one private instance WITHOUT unsubscribing: blocks new runs from starting, and asks any run in flight to stop. Everything is kept — the subscription, config, repos, documents, memory, timeline and run history — and resum…
- `replay_connection_delivery` — Re-arm ONE dead delivery so the pump tries it again — the escape hatch for \
- `resume_instance` — Put a PAUSED instance back to work: new runs may start again, and background work (cron, the pump, delivery retries, webhooks) resumes. It does NOT restart runs the pause stopped — those have terminal rows and re-running an objective who…
- `resume_instance_takeover` — Resume a run after a human dealt with what it handed off — a captcha solved, a widget operated, a page signed into. The agent re-checks the page and carries on. Answering a needs_input question is a different call (answer_instance_input)…
- `run_instance_task` — Create a task on the registered local or managed browser runtime for a private instance. The PAGS brain stays in control; the local ProAgentStore runner executes browser capabilities through the relay.
- `run_instance_trigger` — Manually run one configured instance trigger now. This can create tasks, add knowledge, or sync a granted connector folder.
- `send_instance_takeover_input` — Send ONE mouse or keyboard event into a taken-over page (relayed to the real browser over CDP). This is the raw remote-control primitive the console
- `set_instance_runner_node` — Pin one instance to a specific machine, so its runner calls (chat tools, apply, coding) route there — and MOVE it there in the same call: when that machine\
- `start_instance_browser_task` — Start a browser task on a private instance: the agent drives the owner
- `start_instance_loop` — Give an agent an objective and let it work autonomously on the server. Durable: it survives you closing the browser, and its spend is bounded by a budget. Returns a run id — poll it with check_instance_loop.
- `stop_instance_loop` — Ask an autonomous run to stop. Cooperative: the step in flight finishes and settles its spend rather than being killed mid-way. No dry run — call check_instance_loop first to see which run you are about to stop.
- `test_instance_mcp_server` — Connect to a remote MCP endpoint as this instance would and report what is actually true about it: whether it answered, what tools it publishes, and for each tool whether this agent could really CALL it — naming which of the three gates …
- `trigger_agent_deploy` — Trigger the GitHub Actions deploy workflow for an owned agent repo.
- `cancel_instance` — Cancel your subscription and deactivate one private subscribed instance.
- `set_budget_limits` — Patch your per-account AI-spend limits — the two daily circuit breakers and the four per-tree run knobs. Only the fields you pass are changed; anything you omit keeps its stored value. Pass null for a field to clear that override so it i…
- `account_activity` — What every instance on this account is doing right now, in one call —
- `agent_activity` — Get recent activity log for an agent (chat, tool calls, file uploads, etc.).
- `agent_analytics` — Get usage analytics for an agent
- `agent_deploy_status` — Check the latest GitHub Actions deploy runs for an agent repo.
- `agent_info` — Get an agent
- `agent_messages` — The TEMPLATE
- `agent_trace` — Reconstruct the complete, time-ordered timeline of what an agent instance DID — chat turns (chat.in/tool.call/chat.out), apply steps/handoffs/outcomes (apply.*), and failures, interleaved. This is the primary tool for debugging or improv…
- `ask_ticket` — Ask ONE board ticket a question and get the agent
- `billing_status` — Read your billing/plan status (free vs Pro, whether the paywall is enforced, whether a billing account exists). Upgrades happen in the console (browser redirect).
- `check_instance_loop` — Check an autonomous run: status, how many steps it has taken, and why it stopped. Omit run_id to list recent runs for the instance — most of them will be CLOSED, because this listing has no status filter. Read \
- `coding_diagnostics` — Full diagnostics for a coding instance: runner connectivity, terminal sessions, repos, issues. Runner state is two separate measurements —
- `coding_engine_get` — Which coding CLI this instance opens sessions with, and which model it runs. Answers
- `coding_instance_deploy_status` — Latest GitHub Actions workflow runs for a coding instance
- `coding_loop_queue` — List the objectives queued behind an instance
- `coding_loop_trace` — Read the live trace for one autonomous coding loop run by
- `coding_repos_list` — List all repos registered in a coding instance, with their status and active sessions. Answers
- `coding_sessions_list` — List all coding sessions (active + ended) for an instance.
- `coding_terminal` — Read a coding session
- `coding_timeline` — Read what a coding run is DOING, while it is still running — the objective it was given, each instruction sent to the engine, terminal snapshots and the outcome. Call it with no cursor and you get the NEWEST page (rows within a page alwa…
- `connector_status` — Is a file connector connected for your account, and is this deployment configured for it? Returns
- `email_status` — Gmail connection status for the email-access tool (configured? connected?). Connect/disconnect happens in the console.
- `error_summary` — What is RECURRING in the platform error log, rather than what happened last — ask this before list_errors when the question is \
- `export_agent` — A complete JSON backup of an agent TEMPLATE: its catalogue fields, its DO state, and EVERY knowledge document and memory entry it holds. This is the restore-shaped blob (
- `get_account_preferences` — Read your account-wide preferences — the defaults that follow you across every agent:
- `get_agent_board_config` — Read the authenticated creator
- `get_agent_capabilities` — What an agent TEMPLATE declares it can do:
- `get_agent_memory` — The TEMPLATE
- `get_agent_settings_schema` — Read an agent
- `get_agent_state` — The TEMPLATE
- `get_agent_stats_schema` — Read an agent
- `get_apply_tips` — Read the learned per-ATS apply tips for an apply-capable instance (what worked/failed on each ATS host — console Rules & Tips).
- `get_budget_limits` — Read your AI-spend circuit breakers: effective daily ceilings (charged micros + token count), which tier each was resolved from (account / platform / env / default), current rolling 24h consumption, and distance to limit. Use this before…
- `get_creator_dashboard` — Read your creator dashboard: how many agents you own, their active subscribers, total recorded usage, and the per-agent ranking. Account-wide and owner-scoped — an agent with no subscribers still appears with zeroes.
- `get_instance_behaviour_schema` — Read the platform
- `get_instance_board_config` — Read a private instance
- `get_instance_connection_guide` — The ready-made briefing for driving ONE instance: its id, its agent type, its registered repos, the tools it actually exposes with their exact field names, and a worked call_instance_tool example using its real names. Plain Markdown — pa…
- `get_instance_connector_account` — Which of your accounts an instance uses, per connector you hold an account on (e.g. Gmail). Each row carries the
- `get_instance_instructions` — Read a subscribed instance
- `get_instance_loop_limits` — Read the iteration floor and ceiling configured on an instance — the bounds the platform applies to EVERY run it starts, whatever
- `get_instance_loop_presets` — Read the saved objectives an instance offers when a loop starts — each
- `get_instance_memory` — Read a subscribed instance
- `get_instance_operator_manual` — Read the operator manual for a subscribed instance — caller-facing notes about HOW this instance is meant to be driven (not an instruction to the agent). Returns { manual, rules, context }:
- `get_instance_pipeline` — Read back the stored definition of a named declarative pipeline on this instance (issue #464). Returns the full pipeline JSON (steps, sink, etc.) exactly as stored, plus
- `get_instance_settings` — Read a subscribed instance
- `get_instance_state` — Read a subscribed instance
- `get_instance_stats` — Read a subscribed instance
- `get_instance_task` — Read ONE task/ticket on a private instance in full — status, title, description, and whatever the runtime holds for it. Use this after instance_board or instance_task_events names a task you need the detail of. The route prefers the live…
- `get_instance_terminal_session` — Read the terminal session last selected for one instance.
- `get_instance_voice_settings` — Read a subscribed instance
- `get_profile` — Read the authenticated user
- `get_translation_config` — Read a subscribed instance
- `get_usage_dashboard` — Read your subscriber usage dashboard: active instances, chat and AI-call totals, plus the last 30 days by day and by agent. This is a usage measurement, not billing; it does not replace usage_summary
- `grant_instance_connector_folder` — Grant one of your instances access to a folder on a file connector, by share URL or resource id. Returns the created grant including its
- `hint_instance_task` — Attach a hint to a runtime task (guidance the agent reads on its next step, e.g. answering a blocked task
- `ingest_instance_knowledge_url` — Fetch a public web page into your private subscribed instance
- `ingest_repo_status` — List the repositories indexed on a repo-chat instance and each one
- `instance_activity` — Read a subscribed instance
- `instance_board` — Read a private instance
- `instance_messages` — Read recent messages from one of your private subscribed instances, newest page first. The response carries
- `instance_runner_node` — Read which machine ONE instance is pinned to, and which machines it could be pinned to.
- `instance_runtime_status` — Check the registered local or managed browser runtime for one of your private instances.
- `instance_task_events` — Read recent events from a private instance
- `keys_status` — Which AI providers have a BYOK key stored for your account (names only — values are never exposed). Useful when chat says BYOK is required.
- `list_agent_files` — List files stored by an agent (resumes, documents, etc.).
- `list_agent_repo_files` — List files in an owned agent
- `list_agent_tasks` — The standing tasks an instance carries in its own task store — the ones injected into its system prompt every turn, NOT the runtime board (for that use instance_board or get_instance_task). Returns each task with
- `list_agents` — List all published agents on ProAgentStore
- `list_collections` — List all data collections (tables) for an agent. Shows schema and record counts.
- `list_connection_deliveries` — The pump
- `list_connections` — List the agent-to-agent event connections leaving an instance — how a fact it emits (e.g. lead.created) is routed to another agent.
- `list_connectors` — List every connector this deployment knows, resolved for the signed-in account: id, label, auth kind, scopes, grant model, the tools it contributes, whether the deployment is
- `list_errors` — Read the platform error log — persisted failures (key-proxy, sign-in, apply/coding, and workflow crashes) that would otherwise be invisible. Yours by default; scope \
- `list_feedback` — Read what the OWNER said went wrong (#514) — in-session complaints about an agent, each anchored to the turn it is about. Every row carries
- `list_instance_collections` — List all data collections (tables) for one of your subscribed instances. Shows schema and record counts.
- `list_instance_connector_consents` — Read the owner-granted WRITE consent rows for one instance. Each row names its
- `list_instance_connector_grants` — List the folders one of your instances has been granted on a file connector. Each grant carries the
- `list_instance_connectors` — What THIS instance may do with each connector — the per-agent verdict, not the account-level connection. An account connects Drive once, but an agent is only offered a connector when it declares one of that connector
- `list_instance_drive_files` — List the files inside a Google Drive folder one of your instances has been granted.
- `list_instance_files` — List files uploaded to a private subscribed instance (PDFs, documents — the console
- `list_instance_knowledge` — List user-specific knowledge documents in your private subscribed instance.
- `list_instance_mcp_grants` — The outbound-MCP grants on one instance: which remote tools, on which endpoints, this agent is allowed to CALL. Each grant is a (endpoint, tool) pair;
- `list_instance_mcp_input_requests` — Outbound MCP calls that PAUSED because the remote server asked the person for more (an
- `list_instance_tools` — Audit exactly what one of your instances may do. Returns EVERY tool it could run — its built-in agent facilities (memory, tasks, board, fetch_url, knowledge, files, collections) as well as its connector tools — each with this instance
- `list_instance_trigger_events` — Read recent event history for one configured instance trigger, including received/running/succeeded/failed entries.
- `list_instance_triggers` — List webhook, cron, and connector-sync triggers configured on a subscribed private instance.
- `list_knowledge` — List documents in an agent
- `list_mcp_presets` — First-party MCP servers this deployment knows about, as prefilled URLs. A preset is a URL and nothing more: it carries no credential, grants no tool and skips no gate — the endpoint it names goes through the same test, the same per-tool …
- `list_notifications` — Read your notification feed — what your agents and runs have been telling you (a run finished, stopped, or needs you; a deploy; an application). Newest first, each with
- `list_pipeline_runs` — List an instance
- `list_runner_nodes` — List every machine of yours running a ProAgentStore CLI (
- `list_stats_sources` — Read the supported stats-card source catalogue: each source
- `list_supervision` — List the agents a supervisor instance oversees (its direct reports). Supervision is how one agent delegates goals to others.
- `list_trigger_actions` — The trigger action vocabulary, annotated for ONE instance: every action with
- `mcp_audit_log` — Read recent MCP write, runtime, dry-run, denied, and destructive tool audit events for the authenticated account.
- `my_agent` — Read one of YOUR OWN agent templates in full, as its owner — including a DRAFT, which agent_info cannot see at all. agent_info serves the public catalogue projection (
- `my_agents` — List agents owned by the authenticated ProAgentStore creator.
- `my_instances` — List your subscribed runnable agent instances. These are the correct targets for real agent chats. Paused instances are omitted unless include_paused is true.
- `platform_guide` — Get ProAgentStore platform guide
- `platform_health` — Is the platform healthy right now, and where is the time going? Read-only, safe to call at any time, no side effects. Returns one verdict per component —
- `preview_instance_run_continue` — What continuing a STOPPED run would actually carry forward, before spending anything on it (#806). Answers with
- `preview_instance_trigger` — Check a trigger BEFORE creating it. Returns
- `query_instance_records` — Query records from a collection on one of your subscribed instances. Filter by field values, sort, paginate.
- `query_records` — Query records from a collection. Filter by field values, sort, paginate.
- `read_agent_file` — Read a file from an owned agent
- `recent_instances` — The instances THIS account is driving or drove most recently over MCP, each with its latest run
- `record_instance_feedback` — Record something the OWNER says one of their agents got wrong (or did well) — the same row the console
- `resync_instance_personality` — Replace a subscribed instance
- `runner_node_forget_preflight` — Safely inspect whether a machine registration can be forgotten. Returns every alias that would be removed, whether the machine is connected, and ALL pin or open-session blockers. It changes nothing. If
- `sdk_reference` — Get ProAgentStore SDK usage examples
- `search_agent_knowledge` — Semantic search across an agent
- `search_instance_knowledge` — Semantic (vector) search across a private instance
- `system_status` — Full diagnostics for a coding instance: runner connectivity, node name, tmux sessions, repos, issues — and
- `ticket_thread` — Read the question-and-answer thread on ONE board ticket, oldest first (#150). Use it before ask_ticket to see what has already been asked and answered. Get task_id from instance_board (
- `usage_summary` — Token usage + ESTIMATED value across all your agents over a time
- `vector_stats` — What
- `whoami` — Which account this connection is signed in as: id, login, sign-in provider — the string
- `add_instance_knowledge` — Add user-specific knowledge to your private subscribed instance. This does not alter the creator
- `add_knowledge` — Add a document to an agent
- `apply_account_coding_default` — Apply your saved account-wide coding CLI default to reachable idle coder sessions now. This is the MCP equivalent of the Preferences page
- `batch_write_agent_files` — Create or overwrite multiple files in an owned agent
- `chat_with_my_agent` — Send a test message to one of YOUR OWN agent TEMPLATES. This is the creator conversation returned by agent_messages, not chat_with_instance
- `coding_engine_set` — Choose which coding CLI this instance opens sessions with, and optionally the model it runs — e.g. switch to another engine, or off a model whose usage limit is spent.
- `coding_repo_add` — Add a repo to a coding instance. A coding repo is BOTH a local checkout the engine runs in AND its GitHub identity, set together in this one call:
- `create_agent` — Create a new agent on ProAgentStore.
- `create_agent_task` — Add a standing task to an instance
- `create_agent_version` — Save the current state of one of YOUR OWN agent TEMPLATES as an immutable version snapshot. This does not change the live template; it creates a rollback point. Preview shows the exact route, then confirm to write the version.
- `create_collection` — Create a new data collection for an agent. Define fields with types and indexing.
- `create_connection` — Route an event one agent emits to another agent — the
- `create_instance_ticket` — Put a ticket on an instance
- `create_instance_trigger` — Create a webhook, cron, or connector-sync trigger on a subscribed private instance. Use sync_connector with config.provider and config.grant_id for Google Drive or Zoho WorkDrive folder syncs. An action the instance
- `create_supervision` — Put one agent in charge of another: the supervisor may then delegate goals to the subordinate. Rejected if the SUPERVISOR
- `import_instance_drive_file` — Copy one Google Drive file into an instance
- `import_instance_workdrive_file` — Copy one Zoho WorkDrive file into an instance
- `ingest_repo` — Index a GitHub repository into a read-only repo-chat instance (the
- `insert_instance_record` — Insert a new record into a collection on one of your subscribed instances. Respects the collection
- `insert_record` — Insert a new record into a collection.
- `mark_all_notifications_read` — Mark EVERY unread notification in your feed read — account-wide, across all instances, not just one page of list_notifications. Read-state only; it answers nothing. Call list_notifications with unread_only:true first if you need to see w…
- `mark_notification_read` — Mark ONE notification read, by the
- `plan_agent_builder` — Turn a natural-language request into the deterministic agent-builder plan the creator UI uses: proposed template fields, runtime, connectors, warnings and the action it would take. Planning changes nothing; inspect this result before exe…
- `promote_board_item` — Make a board card a first-class ticket (#757): its runs are then stored as the ticket
- `register_instance_runtime` — Register a local or managed ProAgentStore browser runtime for one of your private instances. Use this before run_instance_task for browser-capable agents.
- `rename_instance` — Set (or clear) a subscribed instance
- `resolve_feedback` — Close the loop on one piece of feedback: set its status and record the issue it became. This is what keeps the backlog honest — a complaint filed as a GitHub issue (github_create_issue) is stamped with the URL so it is not filed twice, a…
- `rollback_agent_version` — Replace an agent TEMPLATE
- `runner_setup` — Read the setup checklist for a coding agent that runs on your own machine (e.g. a
- `runner_update` — Update a machine
- `scaffold_agent` — Create a ProAgentStore agent and scaffold its GitHub repo from a starter template. Requires PAGS token plus GITHUB_TOKEN configured on the MCP worker.
- `set_account_preferences` — Change your account-wide preferences. Patches by SECTION: pass only the sections you mean to change and the rest are left exactly as stored.
- `set_agent_capabilities` — Replace the supplied declared capabilities of an agent TEMPLATE: surfaces, runtime, workflow, tool allowlist and/or custom surfaces. These decide what future subscribers can see and what their runtime is allowed to do; read get_agent_cap…
- `set_agent_settings_schema` — Replace an agent
- `set_agent_state` — Replace the supplied Durable Object state of an agent TEMPLATE — identity, personality, goal, guardrails and welcome message. This changes the seed copied to future subscribers, not a running instance; read get_agent_state first and crea…
- `set_agent_stats_schema` — Replace an agent
- `set_board_item_status` — Move a board card to a different column (or reset it to automation by omitting status). Get valid statuses from instance_board / get_agent_board_config.
- `set_connection_enabled` — Pause or resume an event connection without deleting it. While paused the source
- `set_instance_board_config` — Customize a private instance
- `set_instance_connector_account` — Pin an instance to ONE of your accounts on a connector, so its calls through that connector stop refusing with
- `set_instance_connector_consent` — Set WRITE consent for one connector on one instance — the owner
- `set_instance_instructions` — Replace a subscribed instance
- `set_instance_loop_limits` — Set the iteration floor and ceiling for an instance
- `set_instance_loop_presets` — Save an instance
- `set_instance_mcp_grant` — Grant or revoke ONE remote MCP tool on ONE endpoint for an instance.
- `set_instance_model` — Pick the model that runs a subscribed instance
- `set_instance_operator_manual` — Replace the operator manual for a subscribed instance (max 16000 chars). The manual is caller-facing guidance — notes for the human or MCP client driving this instance. It is NOT injected as an agent instruction; it is fenced as data whe…
- `set_instance_settings` — Update a subscribed instance
- `set_instance_stats` — Add, edit or remove stats cards on YOUR subscribed instance. Patch semantics: pass ops as [{id, card}];
- `set_instance_terminal_session` — Save the terminal session the console
- `set_instance_tool` — Switch one tool on or off for one of your instances — the owner
- `set_instance_voice_settings` — Customise a subscribed instance
- `set_supervision_enabled` — Pause or resume a supervision link without deleting it. While paused the supervisor cannot delegate to that agent and the subordinate escalates past it, but the link keeps its label, its budget defaults and the owner
- `set_translation_config` — Update a subscribed instance
- `subscribe_agent` — Subscribe to a published agent and create your own private runnable instance. Use this before chat_with_instance for real user runs. Pass idempotency_key to make retries safe: a retry with the same key returns the existing instance inste…
- `update_agent` — Update an agent
- `update_agent_board_config` — Update the authenticated creator
- `update_agent_task` — Edit one standing task — its title, description, or
- `update_board_ticket` — Amend an existing board ticket
- `update_instance_knowledge` — Edit one knowledge document on your private subscribed instance IN PLACE — same
- `update_instance_record` — Change fields on ONE existing record in a collection on one of your subscribed instances. The fields you pass are MERGED into the record — fields you omit keep their values; this never replaces the whole record and cannot remove a field.…
- `update_profile` — Update your structured candidate Profile / Job Preferences (string fields only; used by the apply pipeline). Read get_profile first.
- `update_record` — Update fields on an existing record.
- `upload_agent_file` — Upload a file to an agent
- `upload_resume` — Upload/replace the candidate
- `write_agent_file` — Create or overwrite a file in an owned agent
- `write_instance_memory` — Create or update a memory entry on a subscribed instance. Read get_instance_memory first to reuse an existing key instead of creating a near-duplicate.

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Apibase (1384 tools) — https://policylayer.com/tools/io-github-whiteknightonhorse-apibase.md
- Delx Mcp A2a (1068 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- MCP Framework Personal (912 tools) — https://policylayer.com/tools/inggerman-mcps.md
- Hermoso (896 tools) — https://policylayer.com/tools/hermoso.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- Altium-MCP-Suite (817 tools) — https://policylayer.com/tools/altium-mcp-suite.md
- Eda Agent (777 tools) — https://policylayer.com/tools/eda-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-proagentstore-platform · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/io-github-proagentstore-platform