sibyl-memory-mcp

# sibyl-memory-mcp MCP server for [Sibyl Memory Plugin](https://sibyllabs.org/memory). Exposes the local SQLite + FTS5 memory engine to any MCP-compatible agent: **Claude Code, Codex CLI, Cursor, Continue**, anything that speaks Model Context Protocol. ## Install ```bash pip install sibyl-memory-mcp ``` Sibyl Memory runs on Linux, macOS (Apple Silicon and Intel), and Windows through WSL2. Native Windows is not supported. You also need an activated Sibyl Memory account. If you haven't already: ```bash sibyl init ``` This creates `~/.sibyl-memory/credentials.json` (server-issued, HMAC-signed) and a local SQLite database at `~/.sibyl-memory/memory.db`. The MCP server reads both automatically. ## Add to Claude Code Edit `~/.claude/settings.json` (global) or `.mcp.json` (project-local): ```json { "mcpServers": { "sibyl-memory": { "command": "sibyl-memory-mcp" } } } ``` Restart Claude Code. The 8 memory tools (prefixed `memory_*`) become available immediately. ## Add to Codex CLI Edit `~/.codex/config.toml`: ```toml [[mcp_servers]] name = "sibyl-memory" command = "sibyl-memory-mcp" ``` Restart Codex. ## Run with Docker A first-party image is provided at the repo root (`Dockerfile`, `docker-compose.yml`, `.dockerignore`). The image is non-root, runs on a pinned slim Python base, and bakes in no secrets. Memory lives on a mounted volume so it survives container recreation. The MCP server speaks stdio, not HTTP. It is not a daemon you leave running. Run it attached to an MCP client's stdin, or via `docker compose run`. Build: ```bash docker build -t sibyl-memory-mcp:local . ``` First, activate on the host so the mounted volume carries your credentials: ```bash sibyl init ``` Run attached, mounting your host `~/.sibyl-memory` for `memory.db` and `credentials.json`: ```bash docker run -i --rm \ -v "$HOME/.sibyl-memory:/home/app/.sibyl-memory" \ sibyl-memory-mcp:local ``` Note the `-i` (keep STDIN open) and the absence of `-t` (no…