GraphMem is a Ruby on Rails application implementing a Model Context Protocol (MCP) server for graph-based memory management. It enables AI
If you already use Graph Mem, the graph mem mcp server is the piece that lets your assistant work with it directly. GraphMem is a Ruby on Rails application implementing a Model Context Protocol (MCP) server for graph-based memory management. It enables AI assistants and other clients to create, retrieve, search, and manage knowledge entities and their.
GraphMem provides persistent, structured storage for knowledge entities, their relationships, and observations. It's designed as an MCP server that enables AI assistants to maintain memory across sessions, build domain-specific knowledge graphs, and effectively reference past interactions.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Utility — The Utility tool exposed by this serverCursor — The Cursor tool exposed by this serverWindsurf — Edit your Windsurf's mcp_config.json using the same approach as Cursor's. Usually the SSE container doesn't yield any issueAntigravity — SSE doesn't work with Antigravity — Antigravity uses the newer Streamable HTTP transport (POST/DELETE directly to the serverUrl), while the currentSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Configuration is passed through the environment: RAILS_ENV, RAILS_MASTER_KEY, OLLAMA_HOST, OLLAMA_URL, DATABASE_URL, DB_BACKUP_HOST_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Graph Mem's toolset — Utility, Cursor, Windsurf and 1 more — is a fair guide to whether it matches your workflow. It is maintained by steveoro; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Utility | The Utility tool exposed by this server. |
| Cursor | The Cursor tool exposed by this server. |
| Windsurf | Edit your Windsurf's mcp_config.json using the same approach as Cursor's. Usually the SSE container doesn't yield any issue. |
| Antigravity | SSE doesn't work with Antigravity — Antigravity uses the newer Streamable HTTP transport (POST/DELETE directly to the serverUrl), while the current FastMCP gem (v1.6.0) only supports the older SSE dual-endpoint protocol |
{
"mcpServers": {
"graph_mem": {
"url": "http://localhost:3030/mcp/sse",
"headers": { "X-MCP-Client": "Agent-1" }
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| RAILS_ENV | Configuration value read at startup. | Optional |
| RAILS_MASTER_KEY | Credential the server authenticates with. | Yes |
| OLLAMA_HOST | Endpoint or connection string the server talks to. | Optional |
| OLLAMA_URL | Endpoint or connection string the server talks to. | Yes |
| DATABASE_URL | Endpoint or connection string the server talks to. | Yes |
| DB_BACKUP_HOST_PATH | Endpoint or connection string the server talks to. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.