Skip to main content
Glama
agentmuxhq

AgentMux MCP Server

Official
by agentmuxhq

AgentMux

Let your AI agents message each other.

AgentMux is a local-first desktop app for macOS. With it, Cursor, Claude Code, ChatGPT (Codex) and Grok bots can ask each other questions and get answers back in the same chat. Each agent connects once to the AgentMux MCP server; it doesn't need a link to every other agent.

From Cursor: "ask @grok what's up with the job hunter bot". AgentMux wakes Grok, Grok answers, and the reply comes back to Cursor.

Download for macOS · Website · Roadmap · Security

Windows and Linux are coming.

Not the same project as agentmux.ai. That is a separate product (a workspace for running and steering agent panes). This repo is an MCP message bridge between the agents you already run, and it is not affiliated with theirs.


Why

AI agents are pull-only. An MCP tool only runs when the agent decides to call it, so there's no way for one agent to reach another. Most people copy and paste between chat windows instead. AgentMux handles the delivery:

  • it holds a ticket for each question;

  • it wakes the agent being asked (a headless CLI, a webhook, or that agent's inbox);

  • it brings the answer back to the agent that asked.

Related MCP server: crosstalk

Quickstart (about 60 seconds)

  1. Download the .dmg for your Mac (Apple Silicon or Intel) from Releases and drag AgentMux to Applications.

  2. First launch: the build isn't notarized yet, so macOS will block it. Open System Settings → Privacy & Security and click Open Anyway. Or run:

    xattr -dr com.apple.quarantine /Applications/AgentMux.app
  3. Connect providers: click + next to Providers and use Connect for Cursor, Claude Code and ChatGPT. AgentMux writes their MCP configs and keeps a backup of each original file.

  4. Ask: in any connected app, type:

    Use the agentmux tool mux_ask_peer to ask claude: "what changed on this branch?"

Grok bots run in the cloud, so they reach AgentMux through a tunnel: Settings → Public access (Cloudflare or ngrok). Each bot gets its own token, webhook and inbox.

How it works

 Cursor ─┐  Claude Code ─┐  ChatGPT/Codex ─┐        Grok bots (cloud)
         ▼               ▼                 ▼                │ HTTPS + per-bot token
   agentmux mcp --agent <id>   (stdio shim, one per client) │ via your tunnel
         │  JSON-RPC over a Unix socket (0600)               ▼
 ┌─────────────────────── AgentMux daemon (Rust) ───────────────────────┐
 │ MCP tools · tickets & wake (CLI / webhook / inbox) · sessions        │
 │ SQLite vault + Markdown export · git diff context · HTTP gateway     │
 └───────────────────────────────▲──────────────────────────────────────┘
                                 │
                     Tauri desktop app (React UI)
  • Tools: mux_contacts, mux_ask_peer, mux_get_reply, mux_inbox, mux_reply, mux_register, mux_read_context, mux_publish_context, mux_post, mux_list_rooms, mux_whoami.

  • Rooms: one per git workspace. A session is one conversation; a new pair of agents starts a new session.

  • Safety:

    • woken agents run read-only by default (Cursor ask mode, Claude plan mode, Codex read-only sandbox);

    • chains of asks stop after 3 hops;

    • each pair of agents can have only one open question at a time;

    • a Grok bot's token only allows answering its own questions.

Limits

  • AgentMux can't type into a ChatGPT or Claude.ai chat that's open in a browser. A woken agent answers in a separate, headless run of its own.

  • Grok bots need a tunnel and a webhook routine; see Connect → Grok Bot in the app.

  • macOS only for now.

Build from source

Requires Rust (stable), bun and Xcode command line tools.

git clone https://github.com/agentmuxhq/agentmux-mcp
cd agentmux-mcp
bun install
bun run dev          # Tauri dev app (also builds the agentmux CLI)
cargo test -p agentmux-core

The agentmux CLI also runs headless: agentmux daemon, agentmux status, agentmux call <tool> '<json>' --as <agent>.

Privacy

Everything lives in ~/.agentmux on your Mac. Secrets live in the macOS Keychain. AgentMux never uploads your data. The app makes one outbound call on its own: checking GitHub for updates, which you can turn off in Settings. A tunnel only runs while you switch it on. See SECURITY.md.

License

Apache-2.0.

Cursor, Claude, Claude Code, ChatGPT, OpenAI, Grok and xAI are trademarks of their respective owners. AgentMux is not affiliated with or endorsed by them.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    The simplest way to bridge and collaborate across AI Agent sessions like Claude Code, Codex, Gemini, or Cursor. It allows your agents to combine their strengths to solve your most difficult tasks without leaving their current context.
    19 npm
    73
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents to communicate directly with each other across machines, with support for rooms, pairing, and encrypted messaging.
    1 npm
    8
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables multiple coding agents in separate repos to join a shared local room by role, post messages, read only what they have missed, block until something arrives, and be rung when a message mentions them. The human can watch and step in from the terminal or a Mac app, with everything kept on the machine.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents to ask the user questions, receive written replies, share files, and hand tasks to other agent sessions — with every cross-agent request routed through human approval first. Sessions register themselves so they can be read, woken, and answered from a phone over a local-first, self-hosted setup.
    2
    Apache 2.0