// MCP TOOL REFERENCE

LOOPCTL TOOLS

52 tools from the Loopctl MCP Server, categorised by risk level.

View the Loopctl policy → Token cost: 6,507 tokens →

// ALL 52 LOOPCTL TOOLS

READ 33 tools

Read claim_story Agent claims a contracted story. Uses pessimistic locking to prevent double-claims. Transitions contracted ... Read contract_story Agent acknowledges a story's acceptance criteria to claim the contract. Transitions the story from pending ... Read dispatch Mint an ephemeral api_key for a sub-agent dispatch. The raw_key is returned ONCE — pass it to the sub-agent... Read get_acceptance_criteria List acceptance criteria for a story with their verification status. Read get_cost_anomalies Get cost anomaly alerts — stories or agents that exceed expected token budgets. Optionally filter by project. Read get_cost_summary Get cost/token usage summary for a project. Optionally break down by agent, epic, or model. Read get_progress Get progress summary for a project, including story counts by status. Pass include_cost=true to include cos... Read get_sth Get the latest Signed Tree Head for a tenant's audit chain. Public — no auth required. Read get_story Get full details for a single story by ID. Read get_story_token_usage Get token usage records for a single story. Read get_system_articles List or retrieve system-scoped wiki articles. Public — no auth required. Read get_tenant Get current tenant info. Use to verify connectivity. Read knowledge_agent_usage Return knowledge usage for an agent: total reads, unique articles, top read articles. Pass api_key_id (api_... Read knowledge_analytics_top Return the top accessed knowledge articles for the tenant. Use to identify which articles agents actually r... Read knowledge_article_stats Return per-article usage statistics: total accesses, unique agents, by-type breakdown, and the 10 most rece... Read knowledge_context Get ranked full articles for a task query. Returns best knowledge with linked references. Pass story_id whe... Read knowledge_drafts List draft (unpublished) knowledge articles. Requires orchestrator role. Returns paginated drafts with tota... Read knowledge_get Get full article content by ID. Use after search to read an article in detail. Pass story_id when working o... Read knowledge_ingest Submit a URL or raw content for knowledge extraction. Enqueues an Oban job that fetches the content (if URL... Read knowledge_ingest_batch Submit up to 50 ingestion items in a single request. Each item follows the same shape as knowledge_ingest (... Read knowledge_ingestion_jobs List recent content ingestion jobs for the current tenant. Returns jobs from the last 7 days, max 50 result... Read knowledge_search Search the knowledge wiki by topic. Returns snippets. Pass story_id when working on a loopctl story so read... Read knowledge_unused_articles Return published articles that have not been accessed in the configured time window. Use to identify dead-w... Read list_projects List all projects in the current tenant. Read list_ready_stories List stories that are ready to be worked on (contracted, dependencies met). Returns compact results — use g... Read list_routes List all available API routes on the loopctl server. Read list_stories List stories for a project, optionally filtered by agent_status, verified_status, or epic_id. Returns compa... Read recover_cap Re-mint a capability token for a story you're assigned to. Use after a session crash when you've lost your ... Read report_story Reviewer (a DIFFERENT agent from the implementer) confirms the implementation is done. Chain-of-custody: th... Read report_token_usage Report token usage for a story implementation session. Stores input/output token counts, model name, and co... Read request_review Agent signals that implementation is complete and ready for review. Does NOT change the story status — fire... Read verify_all_in_epic Bulk verify all reported_done, unverified stories in an epic. Convenience endpoint for the orchestrator aft... Read verify_story Orchestrator verifies a reported_done story. Requires a review_record to exist (call review_complete first)...

WRITE 13 tools

Write backfill_story Mark a story as verified when the work was completed outside loopctl (e.g. before the project was onboarded... Write bulk_mark_complete Bulk mark multiple stories as complete in a single API call. Each story entry needs a story_id, summary, an... Write create_project Create a new project in the current tenant. Write create_story Create a single story inside an existing epic. Use this for one-off additions instead of wrapping the story... Write import_stories Import stories into a project from a structured payload (Epic 12 import format). Pass `merge: true` to add ... Write knowledge_archive Archive an article (soft delete). The article is hidden from search, context, and the index but the row is ... Write knowledge_bulk_publish Atomically publish up to 100 draft articles in a single call. REQUIRES LOOPCTL_USER_KEY to be set in the MC... Write knowledge_create Create a new knowledge article. Use to file findings, document patterns, or record decisions discovered dur... Write knowledge_export Export all knowledge articles as a ZIP archive. Because ZIP binary cannot be returned as MCP content, this ... Write knowledge_publish Publish a draft knowledge article, making it visible to all agents. Requires orchestrator role. Write reject_story Orchestrator rejects a story with a reason. Creates a verification_result with result=fail. Uses the ORCH key. Write review_complete Record that a review has been completed for a story. Must be called before verify_story. Uses the ORCH key. Write set_token_budget Set a token budget for a scope (project, epic, story, or agent). Requires orchestrator or user role. Uses t...

DESTRUCTIVE 3 tools

Destructive delete_project Delete a project and all of its dependent resources (epics, stories, audit entries scoped to it). REQUIRES ... Destructive knowledge_delete Delete an article. Under the hood this performs the same soft-delete (archive) as knowledge_archive — use w... Destructive knowledge_unpublish Revert a published article back to draft state. The article stops being visible in agent search/context but...

EXECUTE 3 tools

Execute knowledge_index Load the knowledge wiki catalog at session start. Returns article metadata grouped by category. Pass story_... Execute knowledge_lint Run a lint check on the knowledge wiki to identify stale, low-coverage, or broken articles. Requires orches... Execute start_story Agent starts work on a claimed story. Transitions assigned -> implementing. Uses the AGENT key.

// RUNNING THIS SERVER

The managed route: connect Loopctl through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y loopctl-mcp-server

// FAQ

How many tools does the Loopctl MCP server have? +

The Loopctl MCP server exposes 52 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Loopctl tools? +

Route the Loopctl server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Loopctl tools fall into? +

Loopctl tools are categorised as Read (33), Write (13), Destructive (3), Execute (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.