How to add Multi-MCP to Claude Desktop

Multi-model AI orchestration MCP server for automated code review, chat, compare, and debate in Claude Code. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.

Last updated June 14, 2026 · 32★ · stdio · apikey

Claude Desktop config for Multi-MCP

git clone https://github.com/religa/multi_mcp.git && cd multi_mcp && make install

{
  "mcpServers": {
    "multi-mcp": {
      "command": "/path/to/multi_mcp/.venv/bin/python",
      "args": [
        "-m",
        "multi_mcp.server"
      ]
    }
  }
}

Setup steps

1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
2Paste the Multi-MCP config below under the top-level "mcpServers" key.
3Fill in any placeholder secrets (API keys, paths) in the snippet.
4Save the file, then fully quit and reopen Claude Desktop.
5Open a chat and confirm Multi-MCP's tools appear under the 🔌 tools menu.

Before you start

Python 3.11+
uv (for dependency install / make install)
jq (for automatic Claude Code / OpenCode config via make install)
API key for at least one provider (OpenAI, Anthropic, Google, or OpenRouter)
Optional: respective CLI tools installed for CLI models (Gemini CLI, Codex CLI, Claude CLI)

What Multi-MCP can do in Claude Desktop

chat

Interactive development assistance with repository context awareness; ask a model a question directly.

codereview

Systematic code review workflow with OWASP Top 10 security checks and performance analysis, optionally targeting specific models.

compare

Parallel multi-model analysis that gathers multiple perspectives (e.g., for architectural decisions) using the configured default models.

debate

Multi-agent consensus workflow where models give independent answers and then critique each other for deeper analysis.

models

List all available models and their aliases.

Security

Requires API keys for at least one provider (OpenAI, Anthropic, Google, or OpenRouter), stored in a local .env file or ~/.multi_mcp/.env. Your code and prompts are sent to the configured third-party AI model providers for analysis. CLI models run external CLIs as subprocesses with elevated permissions (auto-edit / full-auto / acceptEdits modes), so only enable CLI models you trust.

Multi-MCP + Claude Desktop FAQ

Where is the Claude Desktop config file?

Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the Multi-MCP config there under the "mcpServers" key and restart the client.

Is Multi-MCP safe to use with Claude Desktop?

Do I need all three AI providers?

No. Just one API key (OpenAI, Anthropic, or Google) is enough to get started.

Does it truly run in parallel?

Yes. The codereview, compare, and debate tools execute all models concurrently with Python's asyncio.gather(), so you get results in the time of the slowest model, not the sum of all response times.

How many models can I run at the same time?

There is no hard limit; in practice 2-5 models work well for most use cases, and tools default to your configured default models (typically 2-3).

View repo Full Multi-MCP page