agentmods.dev

agent-messaging

agent-messaging is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from lizTheDeveloper/ai-agent-messaging. Its token cost is not measured, scanned A, original, MIT.

A message-passing server for AI agents that uses NATS, a system for sending messages between programs. It runs locally with Python and requires a NATS server address and a message namespace.

In plain words
What is it for?
Use it to run the agent-messaging server from a Python command and connect it to NATS using NATS_URL and NATS_NAMESPACE.
Why use it?
It gives agents a configured way to exchange messages when the required NATS service and settings are available.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 2repo 9mo ago A scan tokens not measured original MIT

Good fit Use it to run the agent-messaging server from a Python command and connect it to NATS using NATS_URL and NATS_NAMESPACE.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/lizthedeveloper/ai-agent-messaging/agent-messaging
View source ↗ lizTheDeveloper/ai-agent-messaging
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/lizTheDeveloper/ai-agent-messaging

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-messaging

README.md
[![agentmods](https://agentmods.dev/badge/mcp/lizthedeveloper/ai-agent-messaging/agent-messaging.svg)](https://agentmods.dev/mcp/lizthedeveloper/ai-agent-messaging/agent-messaging)
Your own site
<a href="https://agentmods.dev/mcp/lizthedeveloper/ai-agent-messaging/agent-messaging"><img src="https://agentmods.dev/badge/mcp/lizthedeveloper/ai-agent-messaging/agent-messaging.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-messaging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 12 lines

What it actually says

{
  "agent-messaging": {
    "command": "python",
    "args": [
      "mcp_server/servers/agent_messaging_server.py"
    ],
    "env": {
      "NATS_URL": "nats://localhost:4222",
      "NATS_NAMESPACE": "themultiverse"
    }
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 12 lines scan A 20c9177dcfb4

Subscribe to this mod's changes

agent-messaging is an MCP server published in the GitHub repository lizTheDeveloper/ai-agent-messaging (2 stars, last pushed 9mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude Codeagent-messagingai-agentsasync-pythonfastmcpmcp
Related

Other mcp servers, from other repositories

mcp-superset

MCP server for managing Apache Superset — dashboards, charts, datasets, SQL Lab, access control, and more. Runs locally from the mcp-superset Python package. Needs 3 environment variables to run.

bintocher/mcp-superset · not measured

AynOps

A Model Context Protocol server that gives AI Clients real-time cybersecurity reconnaissance capabilities — WHOIS, DNS enumeration, port scanning, SSL inspection, CVE lookup, IP reputation, ASN lookup and more. Runs locally from the AynOps Python package. Needs 2 environment variables to run.

AynOps/AynOps · not measured

openroad-mcp

OpenROAD MCP server (TypeScript/npx). Runs locally from the openroad-mcp npm package.

The-OpenROAD-Project/OpenROAD-MCP · not measured

sagemath

Model Context Protocol server that provides stateful SageMath computations. Runs locally from the sagemath-mcp Python package.

XBP-Europe/sagemath-mcp · not measured

lucius-mcp

Allure TestOps MCP Server. Runs locally from the lucius-mcp Python package. Needs 3 environment variables to run.

ivanostanin/lucius-mcp · not measured

osm-edit

Review-first MCP server for previewed, version-checked OpenStreetMap road edits from local GPX surveys. Runs locally from the osm-edit-mcp Python package. Needs 3 environment variables to run.

skywinder/osm-edit-mcp · not measured