couchbase-mcp-server
Documentation
Couchbase MCP Server
The Model Context Protocol (MCP) is a protocol for handling interactions between large language models (LLMs) and external systems. This repository implements a Couchbase MCP Server using the Couchbase Node.js SDK, enabling MCP clients (e.g., Claude Desktop) to perform natural language queries on Couchbase Capella clusters.
With this server you can use commands like:
- `Show me the results of SELECT * FROM my_bucket LIMIT 10`
- `Execute this query: SELECT name, age FROM users WHERE active = true`
- `Get me the latest 5 documents from my_bucket`
- `Summarize the latest 5 orders from the orders bucket for me`
Example
The following screenshot shows the MCP server in action with the Claude Desktop client. The user issues a general request in plain English and the MCP server translates it into a SQL++ query that is executed against the Couchbase Capella cluster. The results are then returned to the user in a readable format.
Setup
1. Clone the repository and install dependencies:
git clone git@github.com:hummusonrails/couchbase-mcp-server.git
cd couchbase-mcp-server
npm install2. Create a `.env` file in the root directory and add your Couchbase connection string, username, and password:
COUCHBASE_CONNECTION_STRING=couchbases://your-cluster.cloud.couchbase.com
COUCHBASE_USERNAME=your_username
COUCHBASE_PASSWORD=your_passwordRefer to the `.env.sample` file for the required environment variables.
3. Build the project:
npm run build4. Run the server using Stdio transport:
npx couchbase-mcp-server> [!NOTE]
> The MCP server uses the StdioServerTransport, so it communicates over standard input/output. Ensure that your MCP client (e.g., Claude Desktop) is configured to use a local MCP server.
> Follow the Claude Desktop documentation to set up the MCP client to connect to the local server.
Features
Couchbase Query Tool
- ToolName: `query-couchbase`
- Description: Executes a SQL++ query statement on your Couchbase Capella cluster.
- Usage: When invoked, the server will use the Couchbase Node.js SDK to execute the provided SQL++ query and return the results.
Developing
To work on the project locally:
1. Install dependences:
npm install
npm run build2. Test the server using an MCP client:
Launch your MCP client (e.g., Claude Desktop) configured to connect and invoke the tool using a sample query.
3. Debugging
All logging messages are sent to `stderr` to ensure that `stdout` only contains MCP protocol JSON. Check your logs for detailed connection and error messages.
Contributing
Contributions are welcome! Please feel free to submit a pull request or open an issue with your suggestions. For any changes, ensure you follow the project’s code style.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Frequently asked questions
What is couchbase-mcp-server?
couchbase-mcp-server is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install couchbase-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is couchbase-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/hummusonrails/couchbase-mcp-server and has 1 stars.
Related MCP tools
An MCP server that installs other MCP servers for you JavaScript-based implementation. Trusted by 1400+ developers. Trusted by 1400+ developers.
MCP server for interacting with the iOS simulator JavaScript-based implementation. Trusted by 1200+ developers. Trusted by 1200+ developers.
A Model Context Protocol server that provides read-only access to MySQL databases. This server enables LLMs to inspect database schemas and execute read-only...
This is an MCP server that allows you to directly download transcripts of YouTube videos. JavaScript-based implementation.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others. Built for the Model Context Protocol to enhance AI capabiliti
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP