49 tools from the Loopctl MCP Server, categorised by risk level.
View the Loopctl policy →claim_story Agent claims a contracted story. Uses pessimistic locking to prevent double-claims. Transitions contracted -> assigned. Uses the AGENT key. contract_story Agent acknowledges a story's acceptance criteria to claim the contract. Transitions the story from pending to contracted. story_title and ac_count ... dispatch Mint an ephemeral api_key for a sub-agent dispatch. The raw_key is returned ONCE — pass it to the sub-agent via its launch arguments, never store i... get_acceptance_criteria List acceptance criteria for a story with their verification status. get_cost_anomalies Get cost anomaly alerts — stories or agents that exceed expected token budgets. Optionally filter by project. get_cost_summary Get cost/token usage summary for a project. Optionally break down by agent, epic, or model. get_progress Get progress summary for a project, including story counts by status. Pass include_cost=true to include cost data when available. get_sth Get the latest Signed Tree Head for a tenant's audit chain. Public — no auth required. get_story Get full details for a single story by ID. get_story_token_usage Get token usage records for a single story. get_system_articles List or retrieve system-scoped wiki articles. Public — no auth required. get_tenant Get current tenant info. Use to verify connectivity. knowledge_agent_usage Return knowledge usage for an agent: total reads, unique articles, top read articles. Pass api_key_id (api_keys.id credential) OR agent_id (agents.... knowledge_analytics_top Return the top accessed knowledge articles for the tenant. Use to identify which articles agents actually read. Requires orchestrator role. knowledge_article_stats Return per-article usage statistics: total accesses, unique agents, by-type breakdown, and the 10 most recent events. Requires orchestrator role. knowledge_context Get ranked full articles for a task query. Returns best knowledge with linked references. Pass story_id when working on a loopctl story so reads at... 2/5 knowledge_drafts List draft (unpublished) knowledge articles. Requires orchestrator role. Returns paginated drafts with total_count in meta. Max 20 per page. knowledge_get Get full article content by ID. Use after search to read an article in detail. Pass story_id when working on a loopctl story so reads attribute cor... knowledge_ingest Submit a URL or raw content for knowledge extraction. Enqueues an Oban job that fetches the content (if URL), extracts knowledge articles via LLM, ... 2/5 knowledge_ingest_batch Submit up to 50 ingestion items in a single request. Each item follows the same shape as knowledge_ingest (url OR content, source_type required). R... knowledge_ingestion_jobs List recent content ingestion jobs for the current tenant. Returns jobs from the last 7 days, max 50 results. Requires orchestrator role. knowledge_search Search the knowledge wiki by topic. Returns snippets. Pass story_id when working on a loopctl story so reads attribute correctly. knowledge_unused_articles Return published articles that have not been accessed in the configured time window. Use to identify dead-weight knowledge. Requires orchestrator r... list_projects List all projects in the current tenant. list_ready_stories List stories that are ready to be worked on (contracted, dependencies met). Returns compact results — use get_story for full details. Max 20 per pa... list_routes List all available API routes on the loopctl server. list_stories List stories for a project, optionally filtered by agent_status, verified_status, or epic_id. Returns compact results (no acceptance_criteria/descr... recover_cap Re-mint a capability token for a story you're assigned to. Use after a session crash when you've lost your cap. report_story Reviewer (a DIFFERENT agent from the implementer) confirms the implementation is done. Chain-of-custody: the implementing agent cannot call this. T... report_token_usage Report token usage for a story implementation session. Stores input/output token counts, model name, and cost. Uses the AGENT key. request_review Agent signals that implementation is complete and ready for review. Does NOT change the story status — fires a webhook event for the reviewer. Uses... verify_all_in_epic Bulk verify all reported_done, unverified stories in an epic. Convenience endpoint for the orchestrator after a review pass. Uses the ORCH key. verify_story Orchestrator verifies a reported_done story. Requires a review_record to exist (call review_complete first). Transitions reported_done -> verified.... backfill_story Mark a story as verified when the work was completed outside loopctl (e.g. before the project was onboarded). REFUSED for stories that have any loo... 2/5 bulk_mark_complete Bulk mark multiple stories as complete in a single API call. Each story entry needs a story_id, summary, and review_type. Uses the ORCH key. 2/5 create_project Create a new project in the current tenant. 2/5 create_story Create a single story inside an existing epic. Use this for one-off additions instead of wrapping the story in a bulk import payload. Pass either `... 2/5 import_stories Import stories into a project from a structured payload (Epic 12 import format). Pass `merge: true` to add stories to epics that already exist (oth... 2/5 knowledge_bulk_publish Atomically publish up to 100 draft articles in a single call. REQUIRES LOOPCTL_USER_KEY to be set in the MCP server env (user role — orchestrator r... 2/5 knowledge_create Create a new knowledge article. Use to file findings, document patterns, or record decisions discovered during implementation. 2/5 knowledge_export Export all knowledge articles as a ZIP archive. Because ZIP binary cannot be returned as MCP content, this tool returns a curl command you can run ... 2/5 knowledge_publish Publish a draft knowledge article, making it visible to all agents. Requires orchestrator role. 2/5 reject_story Orchestrator rejects a story with a reason. Creates a verification_result with result=fail. Uses the ORCH key. 2/5 review_complete Record that a review has been completed for a story. Must be called before verify_story. Uses the ORCH key. 2/5 set_token_budget Set a token budget for a scope (project, epic, story, or agent). Requires orchestrator or user role. Uses the ORCH key. 2/5 knowledge_index Load the knowledge wiki catalog at session start. Returns article metadata grouped by category. Pass story_id when working on a loopctl story so re... 3/5 knowledge_lint Run a lint check on the knowledge wiki to identify stale, low-coverage, or broken articles. Requires orchestrator role. Optionally scoped to a proj... 3/5 start_story Agent starts work on a claimed story. Transitions assigned -> implementing. Uses the AGENT key. 3/5 The Loopctl MCP server exposes 49 tools across 4 categories: Read, Write, Destructive, Execute.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Loopctl server.
Loopctl tools are categorised as Read (33), Write (12), Destructive (1), Execute (3). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept