An MCP server that stores persistent, project-scoped memory for Solana and EVM development workflows, including programs, IDLs, PDAs, deployment state, decisions, and audit findings. It can ingest Anchor and Hardhat workspaces, query and diff memory over time, and read Solana CLI context to auto-attribute entries.
From the registry: Persistent, Solana-aware project memory for AI coding agents. Typed entities + git-aware diffs.
$ npm install -g @yksanjo/gmemPlease install the `gmem` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Node.js and npm are required to run the MCP server via npx or a global npm install. (https://nodejs.org/)
Optional prerequisites:
- Optional: install gmem globally — You can install the server globally instead of using npx. Run: `npm install -g @yksanjo/gmem`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@yksanjo/gmem"]
- optional environment variables:
- `GMEM_DB`: Optional path to the SQLite database file to use instead of the auto-resolved per-project database. (example: `<path-to-gmem-db>`)
Note: The README recommends the portable npx path over running from source. The installed binary name is `gmem`. If `GMEM_DB` is not set, the server auto-resolves one database file per project from `Anchor.toml` or the workspace `Cargo.toml`.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GMEM_DBrequiredOverrides the SQLite database file path used for project memory storageMCP server for interacting with the Supabase platform