Coda MCP Server
Provides 15 core tools for managing Coda documents, tables, and rows through HTTP, SSE, and stdio transports. It is specifically optimized for stability with LangSmith Agent Builder and supports document manipulation, data retrieval, and formula execution.
README
Coda MCP Server (Koyeb + LangSmith)
This repo runs a Coda MCP server with:
- Streamable HTTP endpoint:
/mcp(recommended) - Legacy SSE endpoint:
/sse
Quick Start (Koyeb First)
1. Fork or use this repo on GitHub
Use this repository in your own GitHub account (for example RunLittleTurtle/mcp-coda).
2. Create a Koyeb account and connect GitHub
In Koyeb:
- Create a new Web service
- Select your GitHub repo and
mainbranch - Keep Buildpack as builder
- Choose Free / CPU Eco instance
3. Set environment variables
Add these variables in Koyeb:
API_KEY= your Coda API keyPORT=3000

4. Configure port
In Koyeb Ports:
- Port:
3000 - Protocol:
HTTP - Public HTTPS access: enabled

5. Deploy
Click Save and deploy.
After deploy, your public URL will look like:
https://your-service-name.koyeb.app
Health check:
https://your-service-name.koyeb.app/health
MCP endpoint:
https://your-service-name.koyeb.app/mcp
LangSmith Agent Builder Setup
Add an MCP server with:
- Name:
mcp-coda(or your preferred name) - URL:
https://your-service-name.koyeb.app/mcp - Authentication:
Static Headers - Headers: none

Important:
- Use
/mcp(not/and not/ssein Agent Builder) - If tools do not appear after a redeploy, wait a few seconds and reload Agent Builder
Local (minimal)
pnpm install
pnpm build
echo "API_KEY=your-coda-key" > .env
PORT=3000 pnpm start:http
Then test:
http://localhost:3000/healthhttp://localhost:3000/mcp
Environment variables
API_KEYorCODA_API_KEY(required)PORT(optional, default3000)
Credits
- Original project: dustinrgood/coda-mcp
- Early fork lineage: orellazri/coda-mcp
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.