Provides integration with Apache Kafka through Lenses.io, enabling exploration, transformation, and joining of data in Kafka topics across multiple clusters using SQL queries without requiring an additional database.
🌊🔍 Lenses MCP Server 🔎🌊
This is the MCP (Model Context Protocol) server for Lenses, a self-service DataOps tool for engineers building real-time applications with different flavours of Apache Kafka across multiple clusters. Explore, transform and join data in topics from different clusters using SQL, without the need for an additional database.
Try this with the free Lenses Community Edition (restricted by number of users and enterprise features, e.g. OAuth). Requires Lenses v6+.
Table of Contents
1. Install uv and Python
We use uv for dependency management and project setup. If you don't have uv installed, follow the official installation guide.
This project has been built using Python 3.12 and to make sure Python is correctly installed, run the following command to check the version.
2. Configure Environment Variables
Copy the example environment file.
Open .env and fill in the required values such as your Lenses instance details and Lenses API key.
3. Add Lenses API Key
Create a Lenses API key by creating an IAM Service Account. Add the API key to .env with the variable name, LENSES_API_KEY.
4. Install Dependencies and Run the Server
Use uv to create a virtual environment, install the project dependencies in it and then run the MCP server with the FastMCP CLI using the default stdio transport.
To run as a remote server, use the http transport.
To run in Claude Desktop, Gemini CLI, Cursor, etc. use the following JSON configuration.
Note: Some clients may require the absolute path to uv in the command.
5. Optional Context7 MCP Server
Lenses documentation is available on Context7. It is optional but highly recommended to use the Context7 MCP Server and adjust your prompts with use context7 to ensure the documentation available to the LLM is up to date.
6. Running with Docker
The Lenses MCP server is available as a Docker image at lensesio/mcp. You can run it with different transport modes depending on your use case.
Quick Start
Run the server with stdio transport (default):
Run the server with HTTP transport (listens on http://0.0.0.0:8000/mcp):
Run the server with SSE transport (listens on http://0.0.0.0:8000/sse):
Environment Variables
Variable | Required | Default | Description |
| Yes | - | Your Lenses API key (create via ) |
| No |
| Lenses instance URL in format
. Use
for secure connections (automatically uses
for WebSockets) |
| No |
| Transport mode:
,
, or
|
| No |
| Port to listen on (only used with
or
transport) |
Legacy environment variables (for backward compatibility):
LENSES_API_HTTP_URL,LENSES_API_HTTP_PORTLENSES_API_WEBSOCKET_URL,LENSES_API_WEBSOCKET_PORT
These are automatically derived from LENSES_URL but can be explicitly set to override.
Transport Endpoints
stdio: Standard input/output (no network endpoint)
http: HTTP endpoint at
/mcpsse: Server-Sent Events endpoint at
/sse
Building the Docker Image
To build the Docker image locally: