About rabbitmq-mcp
rabbitmq-mcp connects MCP clients to RabbitMQ through its HTTP API, exposing API capabilities as tools. It supports local stdio operation and requires RabbitMQ's management plugin.
Key features
- 01Expose RabbitMQ HTTP API features as tools
- 02Interact with RabbitMQ through MCP clients
- 03Configure connections with environment variables
- 04Optional TLS certificate configuration
- 05Local stdio transport
Use cases
- 01Check queue message counts
- 02Move messages between queues
- 03Purge a dead-letter queue
- 04Check alarms in a virtual host
MCP support
The server exposes RabbitMQ HTTP API capabilities as tools for MCP clients. It currently runs locally over stdio; remote SSE support is planned.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
123Saved tool list · updated 3w ago
This tool takes no parameters.
Details
From the project READMErabbitmq-mcp 
A Model Context Protocol (MCP) server for RabbitMQ, enabling MCP clients to interact with RabbitMQ. This server aims to expose the full range of features available in the official RabbitMQ HTTP API as tools.
MCP is a standardized protocol for managing context between large language models (LLMs) and external systems, such as RabbitMQ. It allows users to ask MCP-enabled AI agents, like Claude Desktop or Cursor, to interact with external systems using natural language.
💬 Example Requests:
- Get me the message count in the inbound signup metrics queue, and if it's over 10,000, move half of them to the metrics overflow queue.
- Purge the outbound email deadletter queue.
- Check if there are any alarms triggered in the production vhost.
These are parseable and actionable requests that an MCP client can handle with this server.
Installation
If you prefer to install locally:
npm install -g rabbitmq-mcp
Or with npx:
npx -y rabbitmq-mcp
Environment Variables
The following environment variables are required to configure a connection to your RabbitMQ instance:
RABBITMQ_HOST– accessible host (e.g.test.abc.cloudamqp.com)RABBITMQ_USERNAME– RabbitMQ usernameRABBITMQ_PASSWORD– RabbitMQ passwordRABBITMQ_MANAGEMENT_PORT– management port (e.g.443or15672)RABBITMQ_PROTOCOL–https(default) orhttp. Usehttpsfor secure connections.
Optional TLS/HTTPS Options
You can provide TLS/HTTPS credentials either as file paths or as environment variable strings:
RABBITMQ_CA– CA certificate (PEM string)RABBITMQ_CERT– Client certificate (PEM string)RABBITMQ_KEY– Client private key (PEM string)RABBITMQ_CA_PATH– Path to CA certificate fileRABBITMQ_CERT_PATH– Path to client certificate fileRABBITMQ_KEY_PATH– Path to client private key file
A cert verification flag exists for debugging, if needed:
RABBITMQ_REJECT_UNAUTHORIZED– Set tofalseto disable server certificate verification (defaults totrue)
MCP Client Configuration Example
As MPC is in rapid development, clients can be finicky to set up correctly. Here's an example best-case config for Claude and Cursor:
{
"mcpServers": {
"rabbitmq-mcp": {
"type": "stdio",
"command": "npx",
"args": ["-y", "rabbitmq-mcp"],
"env": {
"RABBITMQ_HOST": "your-host",
"RABBITMQ_USERNAME": "your-username",
"RABBITMQ_PASSWORD": "your-password",
"RABBITMQ_MANAGEMENT_PORT": "15671",
"RABBITMQ_CA_PATH": "/path/to/rabbit-cert.crt"
}
}
}
}
If you experience initialization errors, you may need to use absolute paths for the command and/or args:
"command": "/local/path/to/node",
"args": ["/local/path/to/rabbitmq-mcp/dist/index.js"],
Important
Currently, this server only supports running locally with stdio. Remote functionality using SSE/streaming is planned for a future update.
Important
The management plugin must be enabled in your RabbitMQ instance to use this server. While there are many options for interacting with RabbitMQ directly via AMQP, the protocol only provides a small subset of the capabilities available through the HTTP API.
License
MIT
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.