Grist

v2.0.33Databasesstable

An MCP server for interacting with the Grist API, enabling language models to manage organizations, documents, tables, and records. It supports advanced features like SQL querying, data filtering, and attachment management for comprehensive Grist dat

grist-mcp-servermcpai-integration
Share:
44
Stars
0
Downloads
0
Weekly
0/5

What is Grist?

Grist is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for interacting with the grist api, enabling language models to manage organizations, documents, tables, and records. it supports advanced features like sql querying, data filtering, and at...

An MCP server for interacting with the Grist API, enabling language models to manage organizations, documents, tables, and records. It supports advanced features like SQL querying, data filtering, and attachment management for comprehensive Grist dat

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP server for interacting with the Grist API, enabling l

Use Cases

Manage Grist organizations, documents, tables, and records.
Execute SQL queries and filter data with advanced capabilities.
Handle attachments and structured data through the Grist API.
nic01asFr

Maintainer

LicenseMIT License
Languagepython
Versionv2.0.33
UpdatedMay 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y grist-mcp-server

Manual Installation

npx -y grist-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Grist

The Grist MCP Server connects AI assistants to Grist, the open-source spreadsheet-database hybrid, via the Grist REST API. It exposes tools for listing organizations, workspaces, documents, tables, columns, and records, as well as creating, updating, and deleting records. Developers and data teams use it to let language models query and manipulate structured Grist data through natural language, enabling automated reporting, data entry, and SQL-backed analysis without leaving their AI client.

Prerequisites

  • Python 3.9+ installed on your system
  • A Grist account with an API key (found under Account Settings > API key)
  • The Grist instance URL (default: https://docs.getgrist.com/api)
  • pip package manager available
  • An MCP-compatible client such as Claude Desktop
1

Install the server via pip

Install the mcp-server-grist Python package from PyPI. This pulls in the MCP SDK and the httpx library used for Grist API calls.

pip install mcp-server-grist
2

Obtain your Grist API key

Log in to your Grist instance, navigate to your profile, and open Account Settings. Under the API section, generate or copy your API key. Keep it safe — the server uses it for all requests.

3

Create a .env configuration file

Create a .env file in your working directory containing your Grist credentials. GRIST_API_HOST should point to your self-hosted instance if you are not using the public Grist cloud.

GRIST_API_KEY=your_grist_api_key_here
GRIST_API_HOST=https://docs.getgrist.com/api
4

Add the server to your MCP client configuration

Open your Claude Desktop configuration file and register the Grist MCP server. The server reads GRIST_API_KEY and GRIST_API_HOST from environment variables passed in the env block.

{
  "mcpServers": {
    "grist": {
      "command": "python",
      "args": ["-m", "mcp_server_grist"],
      "env": {
        "GRIST_API_KEY": "your_grist_api_key_here",
        "GRIST_API_HOST": "https://docs.getgrist.com/api"
      }
    }
  }
}
5

Restart Claude Desktop and verify connection

Quit and relaunch Claude Desktop. In a new conversation, ask Claude to list your Grist organizations. A successful response confirms the server is authenticated and reachable.

Grist Examples

Client configuration

Complete claude_desktop_config.json entry for the Grist MCP server using the Python module invocation and environment-variable-based credentials.

{
  "mcpServers": {
    "grist": {
      "command": "python",
      "args": ["-m", "mcp_server_grist"],
      "env": {
        "GRIST_API_KEY": "your_grist_api_key_here",
        "GRIST_API_HOST": "https://docs.getgrist.com/api"
      }
    }
  }
}

Prompts to try

Example natural language prompts that exercise the eight tools exposed by the server.

- "List all Grist organizations I have access to."
- "Show me all documents in the workspace named 'Finance'."
- "List the columns of the 'Invoices' table in document ID abc123."
- "Add a new record to the 'Expenses' table with Category='Travel' and Amount=450."
- "Find all records in the 'Projects' table where Status equals 'Active' and sort by Deadline."

Troubleshooting Grist

Authentication error: 403 Forbidden when calling any tool

Verify that GRIST_API_KEY is correct and has not expired. Regenerate it in Grist Account Settings and update the env block in claude_desktop_config.json, then restart Claude Desktop.

Connection refused or timeout when GRIST_API_HOST is a self-hosted instance

Confirm the Grist server is running and reachable from your machine. Check that GRIST_API_HOST includes the /api path suffix and uses https:// if TLS is enabled on the server.

Module not found error when starting the server

Ensure you installed mcp-server-grist in the same Python environment that the command in your config points to. Use an absolute path to the Python executable (e.g., /usr/local/bin/python3) if needed.

Frequently Asked Questions about Grist

What is Grist?

Grist is a Model Context Protocol (MCP) server that mcp server for interacting with the grist api, enabling language models to manage organizations, documents, tables, and records. it supports advanced features like sql querying, data filtering, and attachment management for comprehensive grist dat It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Grist?

Install via npm with the command: npx -y grist-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Grist?

Grist works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Grist free to use?

Yes, Grist is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Grist?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides