// MCP TOOL REFERENCE

MERIDIAN TOOLS

42 tools from the Meridian MCP Server, categorised by risk level.

View the Meridian policy → Token cost: 3,551 tokens →

// ALL 42 MERIDIAN TOOLS

READ 24 tools

Read answer_hitl Answer a pending HITL request programmatically. Marks it answered so the waiting session can resume. Use li... Read dismiss_hitl Dismiss a HITL request (won't-answer / no longer relevant). Stays in audit trail. Use list_hitl_requests to... Read get_context_block Return a compact plain-text project context block (north star, sprint, pending sprint items, recent tasks, ... Read get_goal Read the current goal state. Read get_hitl_request Poll a HITL request for the human's answer. Returns the row including status ('pending'|'answered'|'dismiss... Read get_notes List project notes (newest first). Optional ?tag substring filter. Read get_pinned_decisions List pinned decisions (active only by default, newest first). Read get_project_by_name Look up a project by name (case-insensitive substring match). Returns the first hit with id, name, and sprint. Read get_run_transcript Return the full transcript of the executor_run for the given session. The transcript accumulates every log_... Read get_session_brief Single-call session orientation - returns sprint focus, pending sprint items, recent tasks, any blocking fa... Read get_sprint_notes Get all ephemeral scratch-pad notes for the current session. Shown at the top of session briefs so every co... Read get_tasks Get recent tasks across all sessions. Read get_workspace_decisions List workspace-level pinned decisions (active only by default, newest first). Read get_workspace_notes List workspace-level notes (newest first). Optional ?tag substring filter. Read get_workspace_settings Read workspace-global default settings (applies across ALL projects in this workspace): hitl_auto_answer_de... Read idle_until_session_done Poll every 30 seconds until another session is closed or archived. Use this when you need to wait before ed... Read list_hitl_requests List HITL requests for a project without needing UUIDs. Returns pending queue by default; pass status='all'... Read list_projects Call first when project_id is unknown. Returns [{id, name, sprint, created_at}] newest first. Read list_sessions List active sessions for a project. Useful for planning chat to see what's currently running before filing ... Read log_task Log a task this session completed or is working on. Valid statuses: pending, in_progress, done, failed, bac... Read release_file Release a file lock held by this session. Read request_hitl Surface a question to the human-in-the-loop queue. urgency='blocking' means this session pauses until answe... Read search_all Universal search across all project content: tasks, notes, pinned decisions, and sprint items. Uses LIKE ma... Read search_tasks Search tasks by keyword or natural-language query. Uses trigram similarity on Postgres, LIKE on SQLite. Ret...

WRITE 15 tools

Write add_note Add a per-project wiki note (setup, gotcha, howto, env, ...). Free-form title/body; comma-separated tags op... Write add_sprint_note Add an ephemeral note to the current session's scratch pad. Use for constraints, blockers, working assumpti... Write add_workspace_note Add a workspace-level wiki note that applies across ALL projects in this workspace (onboarding, cross-cutti... Write checkpoint Save progress mid-session. Runs auto_capture (buckets done tasks into a note), generates a delta handoff, a... Write claim_file Claim exclusive edit rights on a file path for this session. Locks auto-expire after 2 hours. Write create_project Create a new Meridian project. Write generate_handoff Generate a context handoff. mode='full' writes the complete L0/L1/L2 handoff; mode='delta' returns a compac... Write pin_decision Create a pinned decision (editable constitution row). Use for the current authoritative truth that supersed... Write pin_workspace_decision Pin a workspace-level decision that applies across ALL projects (shared architecture, org-wide standards). ... Write register_session Register this Claude session. Call at session start. Write set_executor_config Store per-project executor defaults (repo_path, env_file, test_cmd, test_min, deploy_cmd, shell_type, branc... Write set_goal Set or update the goal state. Write update_decision Patch a pinned decision. Pass new_title + new_body to atomically supersede (creates a new active row, marks... Write update_md_section Propose a replacement for an anchored section of an agent template doc (CLAUDE.md or AGENTS.md). Does NOT w... Write update_workspace_settings Update workspace-global default settings. Pass only the fields you want to change. hitl_auto_answer_default...

DESTRUCTIVE 2 tools

Destructive delete_decision Hard-delete a pinned decision by id. Use when something was filed by mistake or is a duplicate. For retirin... Destructive delete_note Hard-delete a project note by id.

EXECUTE 1 tools

Execute start_session Register session and return goal + recent tasks in one call.

// RUNNING THIS SERVER

The managed route: connect Meridian 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 @meridianmcp/mcp

// FAQ

How many tools does the Meridian MCP server have? +

The Meridian MCP server exposes 42 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Meridian tools? +

Route the Meridian 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 Meridian tools fall into? +

Meridian tools are categorised as Read (24), Write (15), Destructive (2), Execute (1). 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.