# Team Manager MCP MCP server Agent View of the PolicyLayer registry record for Team Manager MCP: identity, probed posture, risk grade, and all 19 tools classified. HTML page: https://policylayer.com/tools/0xadvait-team-manager-mcp ## Facts - Server id: `0xadvait/team-manager-mcp` - Homepage: https://github.com/0xadvait/team-manager-mcp - Registry record: grade F, identity unverified - Lifecycle: active - Rate-limited: no - Tools: 19 - Tool categories present: Destructive, Execute, Read, Write - Tags: 0xadvait team manager mcp, admin, automation - Record last modified: 2026-06-29T18:53:47.815Z ## Tools (19) | Tool | Category | Risk | Record | | --- | --- | --- | --- | | `team_manager_reset` | Destructive | Critical | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-reset.md | | `team_manager_approve_plan` | Execute | High | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-approve-plan.md | | `team_manager_start_room` | Execute | High | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-start-room.md | | `team_manager_find_sources` | Read | Low | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-find-sources.md | | `team_manager_ingest_sources` | Read | Low | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-ingest-sources.md | | `team_manager_onboard` | Read | Low | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-onboard.md | | `team_manager_query_context` | Read | Low | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-query-context.md | | `team_manager_state` | Read | Low | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-state.md | | `team_manager_emit_decision` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-emit-decision.md | | `team_manager_emit_result` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-emit-result.md | | `team_manager_kill_agent` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-kill-agent.md | | `team_manager_plan_room` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-plan-room.md | | `team_manager_post_blackboard` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-post-blackboard.md | | `team_manager_record_checkpoint` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-record-checkpoint.md | | `team_manager_register_agents` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-register-agents.md | | `team_manager_resume_agent` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-resume-agent.md | | `team_manager_set_sources` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-set-sources.md | | `team_manager_update_budget` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-update-budget.md | | `team_manager_write_memory` | Write | Medium | https://policylayer.com/tools/0xadvait-team-manager-mcp/team-manager-write-memory.md | ## Tool descriptions - `team_manager_reset` — Reset the room to a clean state and clear this run - `team_manager_approve_plan` — Approve or request revisions to the Team Manager plan before starting the governed agent room. - `team_manager_start_room` — Start the approved Team Manager room, dispatch the specialist pool, and persist room state to MongoDB Atlas. Sources can be registered before or after start. - `team_manager_find_sources` — Use Bright Data MCP search to discover source URLs for the current room, then optionally register them for ingestion. This is generic search, not a scenario-specific source pack. - `team_manager_ingest_sources` — Fetch the current room - `team_manager_onboard` — Inspect local MCP configuration, report which providers are configured without exposing secrets, and optionally persist user preferences for future room planning. - `team_manager_query_context` — Retrieve relevant blackboard entries, scoped memory cards, and source evidence for an agent using visibility filters and local vector similarity. - `team_manager_state` — Read the current governed room state, including selected agents, source evidence, budget, checkpoints, and decision. - `team_manager_emit_decision` — Compatibility wrapper for decision-shaped rooms. For generic tasks, prefer team_manager_emit_result. - `team_manager_emit_result` — Store the final result for any governed room: decision, deliverable, implementation plan, report, checkpoint, or other task outcome, with claim-to-evidence audit records. - `team_manager_kill_agent` — Record that the MCP host killed or lost an agent after checkpoint persistence. This updates MongoDB state; it does not kill an OS process. - `team_manager_plan_room` — Act as the Team Manager: propose measurement weights, agent roster, execution profiles, memory policy, task-estimated token budgets, and questions for the human before any agents start. - `team_manager_post_blackboard` — Append a source-linked finding, decision, request, progress update, or warning to the shared MongoDB blackboard. - `team_manager_record_checkpoint` — Persist an agent checkpoint to MongoDB agent_performance_records for crash recovery. - `team_manager_register_agents` — Register the actual subagents or worker profiles available in this MCP host. Registered profiles are persisted to MongoDB agent_profiles and used for routing before cold-start templates. - `team_manager_resume_agent` — Return the latest checkpoint context for an agent and mark it resumed in MongoDB. The MCP host is responsible for restarting the actual worker. - `team_manager_set_sources` — Register arbitrary source URLs for the current room. The host can also pass extractedText from another scraper such as Bright Data MCP; no scenario-specific source pack is assumed. - `team_manager_update_budget` — Update group token usage and return threshold actions for the host agent to enforce. - `team_manager_write_memory` — Write private, team, or global memory into MongoDB memory_cards. ## Related servers - UnClick (1658 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md - Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md - Yaver (811 tools) — https://policylayer.com/tools/io-github-kivanccakmak-yaver.md - Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md - Crow (587 tools) — https://policylayer.com/tools/kh0pper-crow.md - Fortimanager (584 tools) — https://policylayer.com/tools/jmpijll-fortimanager-mcp.md - TinyFn (572 tools) — https://policylayer.com/tools/io-tinyfn-tinyfn.md - Mcp (571 tools) — https://policylayer.com/tools/io-github-2s-io-mcp.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=0xadvait-team-manager-mcp · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/0xadvait-team-manager-mcp