Skip to main content

MCP server for communicating with other AI agents via file-based I/O

Project description

Other Agents

PyPI version CI Python License: MIT

A unified MCP server to orchestrate multiple AI CLI tools from a single interface.

Other Agents is an MCP server that lets you communicate with multiple AI command-line tools—Claude, Gemini, Codex, and Qwen—through a single, standardized protocol.

┌─────────────────────────────────────────────────────────────┐
│                      MCP Client                             │
│                (Claude Desktop / Code)                      │
└─────────────────────────┬───────────────────────────────────┘
                          │ MCP Protocol (stdio)
                          ▼
┌─────────────────────────────────────────────────────────────┐
│                 Other Agents MCP Server                     │
│  ┌─────────────────────────────────────────────────────┐   │
│  │  • list_agents    • use_agent    • use_agents       │   │
│  │  • get_task_status               • add_agent        │   │
│  └─────────────────────────────────────────────────────┘   │
└─────────────────────────┬───────────────────────────────────┘
                          │ File-based I/O
                          ▼
┌─────────────────────────────────────────────────────────────┐
│                     AI CLI Tools                            │
│  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐       │
│  │  Claude  │ │  Gemini  │ │  Codex   │ │   Qwen   │  ...  │
│  └──────────┘ └──────────┘ └──────────┘ └──────────┘       │
└─────────────────────────────────────────────────────────────┘

Quick Start

1. Install

pip install other-agents-mcp

2. Configure (~/.config/claude/claude_desktop_config.json on macOS)

{
  "mcpServers": {
    "other-agents": {
      "command": "uvx",
      "args": ["other-agents-mcp"]
    }
  }
}

3. Use in Claude Desktop:

"Ask Gemini to review this code"
"Get Codex's opinion on this function"
"Send this question to all AI tools"

Supported AI CLIs

CLI Command Notes
Claude Code claude Anthropic's official CLI
Gemini CLI gemini Google's Gemini CLI
Codex codex OpenAI Codex (via Cursor)
Qwen qwen Alibaba's Qwen CLI

Each CLI tool must be installed separately on your system.


MCP Tools

list_agents

List available AI CLI tools and their installation status.

use_agent

Send a prompt to a specific AI CLI.

{
  "cli_name": "gemini",
  "message": "Explain this code"
}

Options:

  • run_async: Run in background, returns task_id
  • session_id / resume: Maintain conversation context
  • timeout: Custom timeout in seconds

use_agents

Broadcast a prompt to multiple AI CLIs simultaneously.

{
  "message": "Review this code for bugs",
  "cli_names": ["claude", "gemini"]
}

get_task_status

Check status of async tasks started with run_async: true.

add_agent

Register a custom AI CLI at runtime.


Installation Options

# PyPI (recommended)
pip install other-agents-mcp

# Or run directly with uvx
uvx other-agents-mcp

# Or via Smithery
npx @smithery/cli install other-agents-mcp --client claude

Development

git clone https://github.com/inchan/other-agents.git
cd other-agents
python -m venv venv && source venv/bin/activate
pip install -e ".[dev]"

# Run tests
pytest tests/ -v

# Run server
python -m other_agents_mcp.server

License

MIT - see LICENSE

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

other_agents_mcp-0.0.4.tar.gz (46.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

other_agents_mcp-0.0.4-py3-none-any.whl (27.6 kB view details)

Uploaded Python 3

File details

Details for the file other_agents_mcp-0.0.4.tar.gz.

File metadata

  • Download URL: other_agents_mcp-0.0.4.tar.gz
  • Upload date:
  • Size: 46.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for other_agents_mcp-0.0.4.tar.gz
Algorithm Hash digest
SHA256 4fd8371e4f2e1b3d0b35183e5a80ebca1ff1dbab41ae01e49e54cdf543440a23
MD5 2045693a79cdb6f180ea266bc837e1c1
BLAKE2b-256 e1a770b97738c43768ad34e5a1f5be7503dd15cb11463bfb0ba64f28f5e8b3da

See more details on using hashes here.

File details

Details for the file other_agents_mcp-0.0.4-py3-none-any.whl.

File metadata

File hashes

Hashes for other_agents_mcp-0.0.4-py3-none-any.whl
Algorithm Hash digest
SHA256 bc00fb30d1c9968883743c3b3a6a5c9643ef3fa0ec5eb85af348512a0fb8237c
MD5 4452708b63d1b842ae05e8ddcfdfa2a9
BLAKE2b-256 3ac6f1254cd883c7ef2a688f4f30b8d5f482c851cfd11c7cc70a05b3dedaec8b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page