MCP Server MCP

Baton

By github 👁 1 views ▲ 0 votes

Multi-model AI orchestration: plan a task DAG, route each task to the best capable model.

Homepage Verified source GitHub

Install

uvx baton-orchestrator

Configuration Example

{
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "baton-orchestrator",
      "version": "0.2.1",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "runtimeArguments": [
        {
          "value": "baton-orchestrator[mcp]",
          "type": "named",
          "name": "--from"
        },
        {
          "value": "baton-mcp",
          "type": "positional"
        }
      ],
      "environmentVariables": [
        {
          "description": "Set to 1 to use your Claude Code subscription CLI (claude -p) as a provider.",
          "name": "CLAUDE_CODE_ENABLED"
        },
        {
          "description": "Set to 1 to use your Codex CLI (codex exec) as a provider.",
          "name": "CODEX_ENABLED"
        },
        {
          "description": "Card-billed Anthropic API key (optional; alternative/addition to the subscription CLIs).",
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        },
        {
          "description": "Any OpenAI-compatible endpoint (Gemini / Groq / OpenRouter / DeepSeek / Ollama).",
          "name": "OPENAI_COMPAT_BASE_URL"
        }
      ]
    }
  ]
}

mcp model-context-protocol pypi