# meridian MCP server

Persistent memory, task coordination, and HITL queue for AI coding sessions.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-ajc3xc-meridian
- Repository: https://github.com/meridianmcp/Meridian

## Install
- Command: `npx -y @meridianmcp/mcp`
- Endpoint: https://usemeridian.us/mcp/sse
- Auth: Not captured

## Setup notes
- Package: Npm @meridianmcp/mcp v1.0.2
- Remote endpoint: https://usemeridian.us/mcp/sse

## Tools
- create_project - Create a new Meridian project. Endpoint: https://usemeridian.us/mcp/sse
- register_session - Register this Claude session. Call at session start. Endpoint: https://usemeridian.us/mcp/sse
- start_session - Register session and return goal + recent tasks in one call. Endpoint: https://usemeridian.us/mcp/sse
- get_goal - Read the current goal state. Endpoint: https://usemeridian.us/mcp/sse
- set_goal - Set or update the goal state. Endpoint: https://usemeridian.us/mcp/sse
- log_task - Log a task this session completed or is working on. Valid statuses: pending, in_progress, done, failed, backlog, future, backburner. Endpoint: https://usemeridian.us/mcp/sse
- get_tasks - Get recent tasks across all sessions. Endpoint: https://usemeridian.us/mcp/sse
- search_tasks - Search tasks by keyword or natural-language query. Uses trigram similarity on Postgres, LIKE on SQLite. Returns top matches with similarity score. Endpoint: https://usemeridian.us/mcp/sse
- generate_handoff - Generate a context handoff. mode='full' writes the complete L0/L1/L2 handoff; mode='delta' returns a compact session update (completed + pending + /goal); mode='starter' returns a ≤20-line block for paste-after-/compact or cold start — project_id, start_session command, last 5 completed titles, top 3 pending IDs, /goal; mode='planner' returns strategic context for a claude.ai planning chat. Endpoint: https://usemeridian.us/mcp/sse
- get_context_block - Return a compact plain-text project context block (north star, sprint, pending sprint items, recent tasks, recent decisions, active sessions). mode='full' (default) for Code Handoff into a fresh Claude Code session; mode='chat' for a shorter paste into a new claude.ai conversation. Endpoint: https://usemeridian.us/mcp/sse
- pin_decision - Create a pinned decision (editable constitution row). Use for the current authoritative truth that supersedes earlier statements. category is free-text; suggested values: STRATEGIC, COMPETITIVE, TECHNICAL, TACTICAL, BUSINESS, PRODUCT, ARCHITECTURAL. Endpoint: https://usemeridian.us/mcp/sse
- update_decision - Patch a pinned decision. Pass new_title + new_body to atomically supersede (creates a new active row, marks old as superseded with back-link). Otherwise patches body/title/category/status in place. Endpoint: https://usemeridian.us/mcp/sse
- get_pinned_decisions - List pinned decisions (active only by default, newest first). Endpoint: https://usemeridian.us/mcp/sse
- delete_decision - Hard-delete a pinned decision by id. Use when something was filed by mistake or is a duplicate. For retiring a valid but superseded decision, use update_decision (status=superseded) instead to preserve the audit trail. Endpoint: https://usemeridian.us/mcp/sse
- checkpoint - Save progress mid-session. Runs auto_capture (buckets done tasks into a note), generates a delta handoff, and returns a compact summary with what was done, what's pending, and the suggested next /goal string. Call before context fills up or before ending a session. Endpoint: https://usemeridian.us/mcp/sse
- request_hitl - Surface a question to the human-in-the-loop queue. urgency='blocking' means this session pauses until answered (poll get_hitl_request). urgency='normal'/'high' lands in the dashboard but doesn't block. assigned_to routes to a specific human_id (null = broadcast). Endpoint: https://usemeridian.us/mcp/sse
- get_hitl_request - Poll a HITL request for the human's answer. Returns the row including status ('pending'|'answered'|'dismissed') and answer text. Endpoint: https://usemeridian.us/mcp/sse
- add_note - Add a per-project wiki note (setup, gotcha, howto, env, ...). Free-form title/body; comma-separated tags optional. Endpoint: https://usemeridian.us/mcp/sse
- get_notes - List project notes (newest first). Optional ?tag substring filter. Endpoint: https://usemeridian.us/mcp/sse
- delete_note - Hard-delete a project note by id. Endpoint: https://usemeridian.us/mcp/sse
- get_session_brief - Single-call session orientation — returns sprint focus, pending sprint items, recent tasks, any blocking failures, and pending HITL requests in a compact XML envelope (<500 tokens). Replaces the start_session + get_context_block two-call pattern for worker/automation sessions. Endpoint: https://usemeridian.us/mcp/sse
- list_hitl_requests - List HITL requests for a project without needing UUIDs. Returns pending queue by default; pass status='all' to see answered/dismissed items too. Essential for planning chat to see what needs a human decision. Endpoint: https://usemeridian.us/mcp/sse
- answer_hitl - Answer a pending HITL request programmatically. Marks it answered so the waiting session can resume. Use list_hitl_requests to find request IDs. Endpoint: https://usemeridian.us/mcp/sse
- dismiss_hitl - Dismiss a HITL request (won't-answer / no longer relevant). Stays in audit trail. Use list_hitl_requests to find request IDs. Endpoint: https://usemeridian.us/mcp/sse
- list_sessions - List active sessions for a project. Useful for planning chat to see what's currently running before filing new sprint items. Endpoint: https://usemeridian.us/mcp/sse
- add_sprint_note - Add an ephemeral note to the current session's scratch pad. Use for constraints, blockers, working assumptions valid only this session. Notes are auto-deleted when the session closes. Endpoint: https://usemeridian.us/mcp/sse
- get_sprint_notes - Get all ephemeral scratch-pad notes for the current session. Shown at the top of session briefs so every cold start sees active constraints. Endpoint: https://usemeridian.us/mcp/sse
- get_run_transcript - Return the full transcript of the executor_run for the given session. The transcript accumulates every log_task description logged during the run, with timestamps. Useful for post-session review or handoff. Endpoint: https://usemeridian.us/mcp/sse
- search_all - Universal search across all project content: tasks, notes, pinned decisions, and sprint items. Uses LIKE matching (SQLite) or ILIKE (Postgres). Returns grouped results: {tasks, notes, decisions, sprint_items, total}. Endpoint: https://usemeridian.us/mcp/sse

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.ajc3xc
- Version: 1.0.2
- Runtime: Npm
- Transports: HTTP, STDIO
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jun 2, 2026
- Source: https://registry.modelcontextprotocol.io