MCP Server for Cursor Integration
LocalAbout MCP Server for Cursor Integration
MCP Server for Cursor Integration connects Cursor with documentation stored in Coda.io tables. It queries multiple tables and includes caching, REST endpoints, and cache and health management.
Key features
- 01Coda.io API integration
- 02Queries multiple tables
- 03Response caching
- 04REST API endpoints
- 05Health and cache management
Use cases
- 01Query Coda.io documentation from Cursor
- 02Search across documentation tables
- 03Check server health and cache status
MCP support
The server provides a context endpoint for Cursor and other MCP clients to query Coda.io documentation.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Server for Cursor Integration
A Managed Context Provider (MCP) server that integrates Cursor with Coda.io documentation. This server provides context-aware responses by querying your Coda.io documentation tables.
Features
- Integration with Coda.io API
- Caching system for improved performance
- RESTful API endpoints
- Support for multiple Coda tables
- Health check and cache management endpoints
Prerequisites
- Node.js (v14 or higher)
- A Coda.io account with API access
- A Coda.io document with relevant tables
Setup
- Clone the repository
- Install dependencies:
npm install - Create a
.envfile based on.env.example:cp .env.example .env - Update the
.envfile with your Coda.io credentials:CODA_API_TOKEN: Your Coda.io API tokenCODA_DOC_ID: Your Coda.io document ID
Running the Server
Development mode:
npm run dev
Production mode:
npm start
Tunneling with ngrok
To expose your local server to the internet using ngrok:
-
Install ngrok:
npm install -g ngrok -
Start your MCP server (in a separate terminal):
npm start -
Create a tunnel to your local server:
ngrok http 3000 -
Ngrok will provide you with a public URL (e.g.,
https://xxxx-xxxx-xxxx.ngrok-free.app) -
Update your
mcp.jsonfile with the ngrok URL:{ "mcpServers": { "Coda MCP": { "url": "https://xxxx-xxxx-xxxx.ngrok-free.app/context", "method": "POST", "headers": { "Content-Type": "application/json" } } } }
Note: The ngrok URL will change each time you restart ngrok unless you have a paid account. Make sure to update your mcp.json file with the new URL when it changes.
API Endpoints
Get Context
POST /context
Body: { "query": "your search query" }
Health Check
GET /health
Cache Management
POST /cache/clear
GET /cache/stats
Coda.io Integration
The server expects the following tables in your Coda.io document:
- Jira Tickets
- API Documentation
- Architecture Decisions
You can modify the table names in src/services/mcp.service.js to match your Coda.io document structure.
Error Handling
The server includes comprehensive error handling for:
- API request failures
- Invalid queries
- Cache management
- Server errors
Contributing
Feel free to submit issues and enhancement requests!
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.