mcpField
B
Baton

Baton

Local
github.com/ribato22AI & Agents
Repository

About Baton

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

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ribato22-baton": {
      "command": "uvx",
      "args": [
        "baton-orchestrator"
      ],
      "env": {
        "CLAUDE_CODE_ENABLED": "<CLAUDE_CODE_ENABLED>",
        "CODEX_ENABLED": "<CODEX_ENABLED>",
        "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
        "OPENAI_COMPAT_BASE_URL": "<OPENAI_COMPAT_BASE_URL>"
      }
    }
  }
}
Run commanduvx baton-orchestrator
Environment variables to set
CLAUDE_CODE_ENABLEDSet to 1 to use your Claude Code subscription CLI (claude -p) as a provider.
CODEX_ENABLEDSet to 1 to use your Codex CLI (codex exec) as a provider.
ANTHROPIC_API_KEYSecretCard-billed Anthropic API key (optional; alternative/addition to the subscription CLIs).
OPENAI_COMPAT_BASE_URLAny OpenAI-compatible endpoint (Gemini / Groq / OpenRouter / DeepSeek / Ollama).

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypibaton-orchestrator0.2.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.