lily-memory-mcp

Self-hosted MCP server for Claude: GitHub read/write tools (from lily-github-mcp-bridge) plus persistent memory on Turso.

Each memory entry = your prompt + Claude's plan + the result.

The flow

1. You ask for something.

2. Claude calls memory_save (prompt + plan) → status planned, returns an id.

3. Claude does the work.

4. Claude calls memory_update (id + result + status done|partial|failed).

5. Next prompt: repeat. Claude starts with memory_search / memory_timeline to recall.

The server sends these instructions to Claude automatically on connect.

Related MCP server: GitHub MCP Server

Tools

GitHub (unchanged): get_file_contents, create_or_update_file, delete_file, list_branches, create_branch, push_files. Memory: memory_save, memory_update, memory_search, memory_timeline, memory_get, memory_forget (soft delete).

Search/timeline return compact rows; memory_get returns full entries (keeps token use low).

Setup

1. Turso: turso db create lily-memory → turso db show lily-memory --url → turso db tokens create lily-memory.

2. Render: new Web Service from this repo (or use render.yaml). Build: npm install && npm run build, start: npm start.

3. Env vars: copy .env.example. Required: GITHUB_TOKEN, MCP_ADMIN_SECRET, MCP_BASE_URL, ALLOWED_REPOS, TURSO_DATABASE_URL, TURSO_AUTH_TOKEN.

4. claude.ai: Settings → Connectors → Add custom connector → https://<your-service>/mcp, approve with the admin secret.

5. Keep-alive: the built-in self-ping runs every 10 min (SELF_PING=false to disable). An external pinger (UptimeRobot) on /health is a good second layer.

If Turso is missing/unreachable the GitHub tools still work and memory tools are simply not listed (see logs).

Safety

• Secrets (GitHub/OpenAI-style keys, JWTs such as Turso tokens, private keys, *_TOKEN= values) are redacted before saving. Redaction is pattern-based — not a guarantee.

• Fields are capped at 8,000 characters.

• ALLOWED_REPOS=* lets the PAT reach every repo it can. Narrower: Seizethewind/*,UmakraftCircle/*.

• Optional nightly backup: set BACKUP_REPO (a private repo) → memories exported as JSONL via the GitHub API.

Develop

npm test runs the memory tests (uses Node's built-in SQLite with FTS5 as a stand-in for libSQL). npm run build compiles src/ to dist/.