5602578b2f
This PR does three things: 1. Executes synchronous tool calls in thread pool allowing for up to 4 + # of CPUs executions in parallel. 2. Makes force quitting via double SIGINT/SIGTERM possible and via single SIGINT/SIGTERM + graceful shutdown timeout expiry possible, even if there are active connections. 3. Sets `timeout_graceful_shutdown` to `ARCADE_UVICORN_TIMEOUT_GRACEFUL_SHUTDOWN` env var if set, else defaults to 15. 4. Disable the worker health check span to reduce noise Tradeoffs: Since this PR introduces executing synchronous tools via `await asyncio.to_thread(func, **func_args)`, this means that there is no way for the thread to be killed until it finishes. The ramifications of this is that the force quitting logic that is also implemented in this PR has to be very harsh `os._exit(1)` just in case there is a sync tool actively executing. This means that `MCPApp` teardown logic will not execute when force quitting is required. Although this was already the case because we weren't previously able to force quit! This tradeoff is justified for now since "parallel" tool executions will relieve us of many worker timeouts that we are seeing in prod. Future work: Minimize/eliminate the need for `os._exit(1)` such that `MCPApp` teardown logic will always execute, even when force quitting. The solution will likely be moving away from `await asyncio.to_thread(func, **func_args)` (while maintaining "parallelism" and then utilize the `TaskTrackerMiddleware` introduced in this PR to cancel all of the active HTTP requests. Resolves PLT-713 |
||
|---|---|---|
| .. | ||
| arcade_mcp_server | ||
| Makefile | ||
| pyproject.toml | ||
| README.md | ||
Arcade MCP Server
Arcade MCP (Model Context Protocol) Server enables AI assistants and development tools to interact with your Arcade tools through a standardized protocol. Build, deploy, and integrate MCP servers seamlessly across different AI platforms.
Quick Links
- Quickstart Guide - Get up and running in minutes
- Walkthrough - Learn by example
- API Reference - MCPApp API documentation
Features
- 🚀 FastAPI-like Interface - Simple, intuitive API with
MCPApp - 🔧 Tool Discovery - Automatic discovery of tools in your project
- 🔌 Multiple Transports - Support for stdio and HTTP/SSE
- 🤖 Multi-Client Support - Works with Claude, Cursor, and more
- 📦 Package Integration - Load installed Arcade packages
- 🔐 Built-in Security - Environment-based configuration and secrets
- 🔄 Hot Reload - Development mode with automatic reloading
- 📊 Production Ready - Deploy with Docker, systemd, PM2, or cloud platforms
Getting Started
Installation
pip install arcade-mcp-server
Create Your First Server
from arcade_mcp_server import MCPApp
from typing import Annotated
app = MCPApp(name="my-tools", version="1.0.0")
@app.tool
def greet(name: Annotated[str, "Name to greet"]) -> str:
"""Greet someone by name."""
return f"Hello, {name}!"
if __name__ == "__main__":
app.run()
Run Your Server
# For development
python my_tools.py
# For Claude Desktop
python -m arcade_mcp_server stdio
# For HTTP clients
python -m arcade_mcp_server --host 0.0.0.0 --port 8080
Community
Analytics & Privacy
Arcade MCP Server collects anonymous usage data to help us improve the service and debug issues. We track "MCP server start" events to understand server usage patterns and reliability.
What We Track
When the server starts, we collect the following information:
- Server configuration: transport type (
httporstdio), host, port - Server metadata: tool count, server version
- Runtime environment: Python version, OS type and release
- Timing: device timestamp
- Errors: error messages (if startup fails)
Privacy
- For anonymous users: Events are tracked with an anonymous ID and no user profile is created
- For authenticated users: Events are linked to your account to help us provide better support
- No sensitive data (credentials, tool inputs/outputs, or personal information) is ever collected
Opt Out
To disable usage tracking, set the environment variable ARCADE_USAGE_TRACKING to 0.
License
Arcade MCP Server is open source software licensed under the MIT license.