Un serveur MCP (Model Context Protocol) pour interagir avec l'API Grist. Ce serveur permet d'accéder et de manipuler les données Grist directement
Grist mcp server lets Claude, Cursor and other MCP clients work with Grist directly. Un serveur MCP (Model Context Protocol) pour interagir avec l'API Grist. Ce serveur permet d'accéder et de manipuler les données Grist directement depuis des modèles de langage comme Claude.
Un serveur MCP (Model Context Protocol) pour interagir avec l'API Grist. Ce serveur permet d'accéder et de manipuler les données Grist directement depuis des modèles de langage comme Claude.
The server is distributed via PyPI as mcp-server-grist, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.
Before the server will start you need to supply 4 environment variables: GRIST_API_KEY, GRIST_API_URL, GRIST_API_HOST, MOUNT_PATH. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Grist sits in that group. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
#### Version Docker
```json
{
"mcpServers": {
"grist-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "GRIST_API_KEY=votre_clé_api",
"-e", "GRIST_API_HOST=https://docs.getgrist.com/api",
"mcp/grist-mcp-server"
]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GRIST_API_KEY | Credential the server authenticates with. | Yes |
| GRIST_API_URL | Endpoint or connection string the server talks to. | Yes |
| GRIST_API_HOST | Endpoint or connection string the server talks to. | Optional |
| MOUNT_PATH | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.