About mcp-zmq
mcp-zmq provides ZMQ messaging operations through an MCP server. It offers tools for publishing, subscribing, request-reply messaging, PAIR socket connections, and server status.
Key features
- 01Publish and subscribe over ZMQ
- 02Send requests and listen for replies
- 03Connect to or bind PAIR sockets
- 04Retrieve ZMQ server status
Use cases
- 01Publishing messages to a ZMQ PUB socket
- 02Subscribing to messages from a ZMQ SUB socket
- 03Handling request-reply messaging with REQ and REP sockets
MCP support
Exposes ZMQ messaging operations as tools for MCP clients, including PUB, SUB, REQ, REP, and PAIR socket operations.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| topic | string | Yes | Message topic/topic filter for subscribers. |
| message | string | Yes | Message payload to publish. |
| bind_address | string | No | Address to bind PUB socket. Defaults to "tcp://127.0.0.1:5555". |
Details
From the project READMEmcp-zmq — MCP server for ZMQ messaging
mcp-name: io.github.daedalus/mcp-zmq
Install
pip install mcp-zmq
Usage
MCP Server
mcp-zmq
Python API
from mcp_zmq import zmq_publish, zmq_subscribe, zmq_send_request, zmq_listen_reply
Available Tools
zmq_publish: Publish a message to a ZMQ PUB socketzmq_subscribe: Subscribe to messages from a ZMQ SUB socketzmq_send_request: Send a request via ZMQ REQ socketzmq_listen_reply: Listen for requests and reply via ZMQ REP socketzmq_pair_connect: Connect to a ZMQ PAIR socketzmq_pair_bind: Bind a ZMQ PAIR socketzmq_status: Get ZMQ server status
Development
git clone https://github.com/daedalus/mcp-zmq.git
cd mcp-zmq
pip install -e ".[test]"
# run tests
pytest
# format
ruff format src/ tests/
# lint
ruff check src/ tests/
# type check
mypy src/
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.