Grist MCP Server

by nic01asFr

49 stars

380 downloads

Not rated

GitHub

About

Integrate with the Grist API to manage relational spreadsheets and data. Requires a Grist API key.

Details

Author: nic01asFr
GitHub stars: 49
Downloads: 380
Categories: Database, Other

- List organizations, workspaces, documents, tables, and columns
- Create, read, update, and delete records in Grist tables
- Execute SQL queries (SELECT only) with parameters and timeouts
- Filter and sort data with advanced querying capabilities
- Manage user access to organizations, workspaces, and documents
- Export documents as SQLite, Excel, or CSV; handle attachments and webhooks
- Validate and create safe formulas for columns

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Grist MCP Server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

From the repository

Install via uvx mcp-server-grist, pip install mcp-server-grist, or Docker. Set environment variables GRIST_API_KEY and optionally GRIST_API_HOST. Configure your MCP client (e.g., Claude Desktop) with the appropriate JSON settings pointing to the server command (uvx, python, or docker). Start the server with mcp-server-grist or python -m mcp_server_grist with desired transport (stdio, streamable-http, or SSE).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "grist mcp server": {
            "mcp-server-grist": {
                "command": "uvx",
                "args": [
                    "mcp-server-grist"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-grist": {
        "command": "uvx",
        "args": [
            "mcp-server-grist"
        ]
    }
}

Grist MCP Server

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.

Structure du projet

mcp-server-grist/
├── src/
│   └── mcp_server_grist/     # Package principal
│       ├── __init__.py       # Point d'entrée du package
│       ├── __main__.py       # Support pour exécution en module
│       ├── version.py        # Gestion de version
│       ├── main.py           # Point d'entrée principal
│       ├── server.py         # Configuration du serveur MCP
│       ├── client.py         # Client API Grist
│       ├── tools/            # Outils MCP organisés par catégorie
│       └── models.py         # Modèles de données Pydantic
├── tests/                    # Tests unitaires et d'intégration
├── docs/                     # Documentation détaillée
├── requirements.txt          # Dépendances Python
├── pyproject.toml           # Configuration moderne du package
├── Dockerfile               # Configuration Docker
├── docker-compose.yml       # Configuration multi-services
├── .env.template            # Template pour variables d'environnement
└── README.md                # Documentation principale

Prérequis

- Python 3.8+
- Une clé API Grist valide
- Les packages Python suivants : fastmcp, httpx, pydantic, python-dotenv

Utilisation à la volée

Via uvx (recommandé)

En utilisant uvx, l'environnement et le téléchargement des paquets se fait à la volée au moment de l'éxécution

uvx mcp-server-grist

Utilisation avec votre Assitant IA favori qui supporte le protocole MCP

La configuration en json est :

{
    "mcpServers": {
        "grist-server": {
            "disabled": false,
            "timeout": 60,
            "type": "stdio",
            "command": "uvx",
            "args": [
                "mcp-server-grist"
            ],
            "env": {
                "GRIST_API_KEY": "ta_cle_API_GRIST"
            }
        }
    }
}

Installation

Via pip

pip install mcp-server-grist

Après l'installation, vous pouvez exécuter le serveur avec :

mcp-server-grist

Utilisation avec Claude Desktop

Pour utiliser ce serveur MCP avec Claude Desktop, ajoutez la configuration suivante à votre fichier mcp_servers.json :

{
  "mcpServers": {
    "grist-mcp": {
      "command": "node",
      "args": [
        "chemin/vers/npm-wrapper/bin/start.js"
      ],
      "env": {
        "GRIST_API_KEY": "votre_clé_api_grist",
        "GRIST_API_URL": "https://docs.getgrist.com/api"
      }
    }
  }
}

Remplacez chemin/vers/npm-wrapper/bin/start.js par le chemin absolu vers le script start.js du wrapper Node.js inclus dans ce package.

Installation en mode développement

Pour contribuer ou personnaliser le serveur :

```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Grist MCP Server

Structure du projet

Prérequis

Utilisation à la volée

Via uvx (recommandé)

Utilisation avec votre Assitant IA favori qui supporte le protocole MCP

Installation

Via pip

Utilisation avec Claude Desktop

Installation en mode développement

Install

More like this

Sequential Thinking

Redis

Filesystem

EverArt

Google Drive

Sqlite