arcade-mcp/libs/arcade-serve
Eric Gustin c205bda092
Release libs for arcade-mcp (#598)
Seeing that arcade-ai==2.2.3 doesn't allow for core, serve, or tdk
versions 3.x.x and that it doesn't know about arcade-mcp-server or
arcade-mcp, I feel confident that we can get this past the release
candidate stage. The current state of our documentation
(docs.arcade.dev) still references the 'old way' of doing things, so we
can gradually introduce these new packages to users without the hassle
of specifying pre release flags when installing

### New packages:
arcade-mcp==1.0.0
arcade-mcp-server==1.0.0

### Breaking change with major bump:
arcade-core==3.0.0 from 2.4.0
arcade-serve==3.0.0 from 2.1.0
arcade-tdk==3.0.0 from 2.5.0

### Deprecated:
arcade-ai==2.2.3
2025-10-03 12:11:25 -07:00
..
arcade_serve MCP Local (#563) 2025-09-25 15:28:15 -07:00
pyproject.toml Release libs for arcade-mcp (#598) 2025-10-03 12:11:25 -07:00
README.md PyPI release arcade-serve and arcade-tdk (#432) 2025-06-13 13:06:11 -07:00

Arcade Serve

Serving infrastructure for Arcade tools and workers.

Overview

Arcade Serve provides the infrastructure for serving Arcade tools:

  • FastAPI Worker: High-performance FastAPI-based worker implementation
  • MCP Server: Model Context Protocol server for tool integration
  • Core Abstractions: Base worker classes and components
  • Authentication: Auth utilities and routing
  • Runtime Management: Tool execution and lifecycle management

Installation

pip install arcade-serve

Usage

To add a toolkit to a hosted worker such as FastAPI, you can register them in the worker itself. This allows you to explicitly define which tools should be included on a particular worker.

Here is an example of adding the math toolkit (pip install arcade-math) to a FastAPI Worker:

import arcade_math
from fastapi import FastAPI
from arcade_tdk import Toolkit
from arcade_serve.fastapi import FastAPIWorker

app = FastAPI()

worker_secret = os.environ.get("ARCADE_WORKER_SECRET")
worker = FastAPIWorker(app, secret=worker_secret)

worker.register_toolkit(Toolkit.from_module(arcade_math))

Here is an example of adding the math toolkit (pip install arcade-math) to a MCP Worker

import arcade_math
from arcade_core.catalog import ToolCatalog
from arcade_serve.mcp.stdio import StdioServer

# 1. Create and populate the tool catalog
catalog = ToolCatalog()
catalog.add_module(arcade_math)


# 2. Main entrypoint
async def main():
    # Create the worker with the tool catalog
    worker = StdioServer(catalog)

    # Run the worker
    await worker.run()


if __name__ == "__main__":
    import asyncio

    asyncio.run(main())

License

MIT License - see LICENSE file for details.