Grist MCP Server

@nic01asFr

Basic information

About Grist MCP Server

MCP server implementation for Grist API integration

Grist MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

Grist MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Grist MCP Server?

Grist MCP Server is a Model Context Protocol (MCP) server that enables large language models like Claude to access and manipulate data in Grist spreadsheets through the Grist API. It provides a structured interface for performing CRUD operations, querying data, and managing Grist resources directly from AI-assisted workflows.

How to use Grist MCP Server?

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).

Key features of Grist MCP Server

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

Use cases of Grist MCP Server

Allow an AI assistant to query and update Grist spreadsheets directly
Automate data management tasks in Grist via natural language commands
Integrate Grist with external MCP‑compatible applications and workflows
Perform complex data analysis using SQL queries from within a chat interface
Manage Grist resources (documents, tables, permissions) programmatically

Frequently asked questions

What are the dependencies and runtime requirements?

Python 3.8+ and the packages `fastmcp`, `httpx`, `pydantic`, and `python-dotenv` are required. You also need a valid Grist API key and access to a Grist instance (cloud or self‑hosted).

What transports are supported?

The server supports `stdio`, `streamable-http`, and `SSE` transports. For HTTP transports you can configure host, port, and path.

How do I authenticate with the Grist API?

Authentication is done via an API key set in the `GRIST_API_KEY` environment variable. The API key can be obtained from your Grist account settings.

Can I run custom SQL queries?

Yes, the server provides an `execute_sql_query` tool for arbitrary SELECT queries, including JOINs and subqueries, with configurable parameters and timeout. The server also has a `filter_sql_query` tool for

Comments

More Other MCP servers

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Codelf

unbug

A search tool helps dev to solve the naming things problem.

14.2K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K