{"id":"7a823d60-a013-48a7-bd28-bab666ecb128","slug":"grist-go-mcp","kind":"mcp","name":"grist-go-mcp","summary":"MCP Server for Grist written in Go","owner":"Quentinchampenois","repoUrl":"https://github.com/Quentinchampenois/grist-go-mcp","license":"MIT","licenseTier":"permissive","trust":"community","stars":0,"match":null,"fewStars":true,"format":"mcp","createdAt":"2025-11-11T20:50:05.000Z","addedAt":"2026-10-21T04:08:53.869Z","logoUrl":"https://avatars.githubusercontent.com/u/26109239?u=f9460a6c2203ee955569e7cb5454b90779ec5c92&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["cloud-infra"],"tags":["grist","grist-api"],"runtime":"go","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-23T20:21:04.584Z","sample":false,"url":"https://conduits.dev/tools/grist-go-mcp","language":"Go","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# Grist MCP Server\n\n[⚠️] Work in progress, not ready for production yet.  \n[⚠️] TODO: Must minimize prompts and responses to limit tokens usage (around 8000 tokens for the sample request)  \n[⚠️] Disclaimer: This is just a for-fun project, not actively maintained, but happy to share and contributions are welcome !\n\nFunctions:\n* ✅ `list_orgs` : List all organizations \n* ✅ `create_workspace`: Creates a new workspace in organization \n* ✅ `create_new_docs`: Creates one or more documents in workspace\n* ✅ `create_new_tables`: Add new tables with columns to a document\n* ☑️ `query_sql`: Query SQL (API not yet available)\n* ☑️ `add_record`: Add a record in a document (API not yet available)\n* ☑️ `get_record`: Get a record in a document (API not yet available)\n\n## Examples\n\nSystem prompt example available at [docs/SYSTEM_PROMPT.md](./docs/SYSTEM_PROMPT.md)\n\n\nPrompt:\n> Create a personal finance tracker in Grist with the following structure:\n> 1. Tables needed:  \n    - Transactions: columns for Date, Description, Category, Amount, Payment Method, and Notes  \n    - Categories: columns for Category Name, Type (Income/Expense), Budget Limit  \n    - Monthly Summary: columns for Month, Total Income, Total Expenses, Net Balance\n\n\n## Getting started\n\n1. Clone the project \n```bash\n$ git clone https://github.com/quentinchampenois/grist-mcp.git \n$ cd grist-mcp\n```\n\n2. Build the server\n```bash\n$ go mod tidy\n$ go build -o grist-mcp-server\n```\n💡 Binary `grist-mcp-server` must be present in `$PATH` to be callable \n\n🚀 MCP Server is ready to use ! But how ?  \nIf you try to run it directly `$ ./grist-mcp-server` process will run but nothing happens, and it's the expected behaviour.\n\n## Use @modelcontextprotocol/inspector to debug\n\nPackage `@modelcontextprotocol/inspector` starts a WebUI to test directly your MCP server, test output based on provided input.\n\n### Requirements\n\n* Node\n\n### How to\n\nStart inspector as following\n\n```bash\n$ npx @modelcontextprotocol/inspector grist-mcp-server\n```\n\nAccess WebUI at http://localhost:6274/?MCP_PROXY_AUTH_TOKEN=<GENERATED_TOKEN>\n\n## Configure client using Cherry studio and Scaleway AI provider\n\nIn this example we will use [Cherry Studio](https://github.com/CherryHQ/cherry-studio) as client and [model qwen3-235b-a22b-instruct-2507 from Scaleway provider](https://www.scaleway.com/en/docs/generative-apis/quickstart/). \n\n### Requirements\n* Configure account on Scaleway and generate API token (~5 minutes)\n* Cherry studio installed\n\n### Configure Qwen3-235b from Scaleway on Cherry Studio\n\nOpen Cherry Studio and configure the Scaleway provider: (cf: README on [another project for full chery studio steps](https://github.com/Quentinchampenois/shell-history-mcp-server?tab=readme-ov-file#configure-client-using-cherry-studio-and-scaleway-ai-provider))\n💡 Very important, setup the environment variables in your cherry studio MCP configuration : \n* `GRIST_ENDPOINT=http://localhost:8484`\n* `GRIST_API_KEY=<YOUR_API_KEY>`, API_KEY from GRIST WebUI\n\n\n\n__🚀 Once Cherry studio let's give a try with a basic prompt__\n\n``` \nI want to manage my tennis club within Grist, including: members, available fields and hours of lessons. \n\nYou must create in Grist : \n* 1 new workspace in my Grist organization\n* 3 documents in this newly created workspace\n```\n\nExample: \n\nPrompt: \n![cherry_studio_prompt.png](docs/cherry_studio_prompt.png)\n\nResult:\n![grist_view.png](docs/grist_view.png)\n\n## Extra\n\n* Source Cherry studio: https://github.com/CherryHQ/cherry-studio\n* Source Scaleway AI (Generative API): https://www.scaleway.com/en/docs/generative-apis/quickstart/\n* Go MCP SDK: https://github.com/modelcontextprotocol/go-sdk/tree/main\n* MCP Inspector: https://modelcontextprotocol.io/docs/tools/inspector"}