Skip to main content
Glama

mcp-memories

An MCP server that captures code build sessions and publishes them to a shared team knowledge base, making past work discoverable via semantic search.

What it does:

  • Auto-captures every agent session via IDE hooks (Cursor, Claude Code)

  • When you call complete_session, it summarizes with Grove AI and embeds with Voyage voyage-code-4

  • Team members search with natural language — vector search + Voyage reranking returns the most relevant past builds

Setup

1. Install and build

npm install
npm run build

2. Configure environment

cp .env.example .env
# Fill in MONGODB_URI, MDB_GROVE_API_KEY, GROVE_BASE_URL, VOYAGE_API_KEY, MEMORIES_AUTHOR

3. Register the MCP server

Add to your IDE's MCP config (e.g. ~/.cursor/mcp.json or Claude Desktop config.json):

{
  "mcpServers": {
    "mcp-memories": {
      "command": "node",
      "args": ["/path/to/mcp-memories/dist/index.js"],
      "env": {
        "MONGODB_URI": "mongodb+srv://...",
        "MEMORIES_DB": "mcp_memories",
        "MDB_GROVE_API_KEY": "...",
        "GROVE_BASE_URL": "...",
        "GROVE_MODEL": "claude-3-7-sonnet",
        "VOYAGE_API_KEY": "...",
        "MEMORIES_AUTHOR": "your.name"
      }
    }
  }
}

4. Set up auto-capture hooks

Cursor — hooks.json is already in .cursor/hooks.json. It fires the capture script on every stop event automatically.

Claude Code — merge the snippet in hooks/claude/settings-snippet.json into your ~/.claude/settings.json, updating the path to point to this repo.

Related MCP server: io.github.norrietaylor/distillery-mcp

Tools

Tool

When to use

capture_activity

Called automatically by hooks, or manually to record what you're working on

complete_session

Call when done — triggers summarization + embedding and publishes to the team

search_memories

Find past builds relevant to what you're about to start

get_overview

See what the team has built, by language / tag / repo

list_recent

Browse the most recently published sessions

Typical workflow

# During a session — automatic (hook fires) or manual:
capture_activity(session_id="abc123", conversation_context="Built JWT auth middleware...")

# When done:
complete_session(session_id="abc123", final_notes="Ended up using RS256 instead of HS256 because...")

# Later, someone else starting similar work:
search_memories(query="JWT authentication middleware Node.js")

MongoDB Atlas setup

The server creates its own indexes on startup, including the Atlas Vector Search index (memories_vector_index, 1024 dimensions, cosine similarity, voyage-code-4). You need an Atlas cluster with Vector Search enabled.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables cross-session memory and recall for AI coding assistants through a git-synced knowledge base, hybrid semantic and TF-IDF search across tool transcripts, and automatic distillation of insights with secrets scrubbing.
      6
      178 npm
      19
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables teams to capture and distill knowledge from sessions, meetings, and feeds into a searchable, vector-embedded graph, then retrieve or synthesize it conversationally via semantic search and citations.
      17
      25
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI coding agents with persistent memory by recording sessions and normalizing them into a searchable knowledge graph, then delivering relevant context at the start of the next session.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI coding assistants to query and store a team's historical development experience through semantic search, so lessons and decisions persist across conversations.
      9
      153 PyPI
      1
      MIT