Versions: * arcade-mcp\==1.0.0rc1 * arcade-mcp-server\==1.0.0rc1 * arcade-core\==2.5.0rc1 * arcade-tdk\==2.6.0rc1 * arcade-serve\==2.2.0rc1 ### Summary Adds first-class MCP support across Arcade, introduces a new MCP server and CLI, unifies the project under the arcade-mcp name, overhauls templates/scaffolding, and improves developer tooling, secrets management, and examples. ### Highlights - **MCP Server & Core** - New MCP server with stdio and HTTP/SSE transports, session management, resumability, and lifecycle handling. - FastAPI-like `MCPApp` for building servers with lazy init; integrated worker+MCP HTTP app option. - Middleware system (logging and error handling), robust exception hierarchy, and Pydantic-based settings. - Async-safe managers for tools, resources, and prompts backed by registries and locks. - Developer-facing, transport-agnostic runtime context interfaces (logs, tools, prompts, resources, sampling, UI, notifications). - Conversion from Arcade ToolDefinition to MCP tool schema; OpenAI JSON tool schema converter. - Parser supports `@app.tool`/`@app.tool(...)` decorators. - **CLI** - New `mcp` command to run MCP servers with stdio or HTTP/SSE. - New `secret` command to set/list/unset tool secrets (supports .env input, preserves original casing for lookups). - `new` command refactored; option to create a full toolkit package with scaffolding. - `chat` command removed. - `serve.py` imports updated to `arcade_serve.fastapi.telemetry`; version retrieval now uses `arcade-mcp`. - `show.py` refactor to use new local catalog utilities. - `display_tool_details` improved: adds “Default” column and handles nested properties. - **Configuration & Discovery** - New `configure.py` to set up Claude Desktop, Cursor, and VS Code to connect to local or Arcade Cloud MCP servers. - Discovery utilities to find/install toolkits, build `ToolCatalog`s, analyze files for tools, load kits from directories (pyproject parsing), and build minimal toolkits. - Better handling of provider API key resolution and evaluation suite loading. - **Templates & Scaffolding** - Reorganized template structure (minimal vs full); moved `.pre-commit-config.yaml`, `.ruff.toml`, license, Makefile, README, tests, and tools layout to correct paths. - Minimal template adds `.env.example` for runtime secret injection. - Template pyproject updated for MCP servers; includes sample server with greeting and secret-reveal tools. - Authorization flow in templates simplified. - **Repo-wide Renaming & Examples** - Migrates references from `arcade-ai` to `arcade-mcp` across READMEs, scripts, and package metadata. - Examples updated (LangChain/LangGraph/AI SDK/TypeScript) and package name changed to `arcade-mcp-sdk`. - **Evals & Core Utilities** - Evals now use OpenAI tooling format (`OpenAIToolList`, `to_openai`); `tool_eval` takes `provider_api_key`. - Core utilities: fixed `does_function_return_value` by dedenting before parse; version bump to `2.5.0rc1` and dependency cleanup. - **Tooling & CI** - `setup-uv-env` action splits toolkit vs contrib dependency installation. - Pre-commit: excludes `libs/arcade-mcp-server/mkdocs.yml` and `libs/tests/` from YAML and Ruff hooks; Ruff per-file ignores (e.g., C901 in `libs/**/*.py`, TRY400 in server docs paths). - Makefile updates for uv env setup, quality checks, tests, builds, and new `shell` target. - Added Makefile to MCP server library to streamline dev workflow. - **Cleanup** - Removed `claude.json` config. - Simplified stdio entrypoint; removed unused imports (`arcade_gmail`, `arcade_search`). ### Breaking Changes - **CLI**: `chat` command removed; use `mcp`, `secret`, and updated `new`. - **Naming**: All users should update references from `arcade-ai` to `arcade-mcp`. - **Templates**: File paths moved; downstream scripts referencing old template locations may need updates. ### Getting Started - Run an MCP server: - `arcade mcp --stdio --toolkits your_toolkit` - `arcade mcp --http --toolkits your_toolkit` - Manage secrets: - `arcade secret set your_toolkit KEY=value` - `arcade secret list your_toolkit` - `arcade secret unset your_toolkit KEY` - Configure clients: - `arcade configure` to set up Claude Desktop, Cursor, and VS Code for local/Arcade Cloud MCP. --------- Co-authored-by: Sam Partee <sam@arcade-ai.com> Co-authored-by: Shub <125150494+shubcodes@users.noreply.github.com>
5.5 KiB
5.5 KiB
Claude Desktop
Claude Desktop supports MCP servers through its configuration system. This guide will help you set up your Arcade MCP server with Claude Desktop.
Prerequisites
- Claude Desktop installed
- Python 3.10+ installed
arcade-aipackage installed (pip install arcade-ai)
Configuration
Claude Desktop reads MCP server configurations from its settings file. The location varies by platform:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Basic Setup
1. Create or Edit Configuration
Add your MCP server to the configuration file:
{
"mcp-servers": {
"arcade-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio"],
"cwd": "/path/to/your/project"
}
}
}
2. Multiple Servers
You can configure multiple MCP servers:
{
"mcp-servers": {
"github-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--tool-package", "github"],
"env": {
"GITHUB_TOKEN": "your-github-token"
}
},
"slack-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--tool-package", "slack"],
"env": {
"SLACK_BOT_TOKEN": "your-slack-token"
}
},
"custom-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio"],
"cwd": "/path/to/custom/tools"
}
}
}
Advanced Configuration
Environment Variables
Pass environment variables to your MCP server:
{
"mcp-servers": {
"my-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--env-file", ".env"],
"cwd": "/path/to/project",
"env": {
"ARCADE_API_KEY": "your-api-key",
"DATABASE_URL": "postgresql://localhost/mydb",
"DEBUG": "true"
}
}
}
}
Custom Python Environment
Use a specific Python virtual environment:
{
"mcp-servers": {
"my-tools": {
"command": "/path/to/venv/bin/python",
"args": ["-m", "arcade_mcp", "stdio"],
"cwd": "/path/to/project"
}
}
}
Debug Mode
Enable debug logging for troubleshooting:
{
"mcp-servers": {
"my-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--debug"],
"cwd": "/path/to/project"
}
}
}
Tool Discovery Options
Auto-Discovery
Automatically discover tools in the current directory:
{
"mcp-servers": {
"local-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio"],
"cwd": "/path/to/tools/directory"
}
}
}
Specific Package
Load a specific Arcade package:
{
"mcp-servers": {
"github": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--tool-package", "github"]
}
}
}
All Installed Packages
Discover all installed Arcade packages:
{
"mcp-servers": {
"all-arcade-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--discover-installed"]
}
}
}
Troubleshooting
Common Issues
Server Not Starting
- Check the command path is correct
- Verify Python is in your PATH
- Ensure
arcade-aiis installed in the Python environment - Check file permissions on the working directory
Tools Not Available
- Verify tools are properly decorated with
@tool - Check the working directory is correct
- Enable debug mode to see tool discovery logs
- Ensure no import errors in your tool files
Authentication Errors
- Verify environment variables are set correctly
- Check API keys and tokens are valid
- Ensure proper escaping of special characters in JSON
Viewing Logs
When using stdio transport, logs are sent to stderr. To capture logs:
{
"mcp-servers": {
"my-tools": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--debug"],
"cwd": "/path/to/project",
"stderr": "/tmp/arcade-mcp.log"
}
}
}
Testing Your Configuration
- Save your configuration file
- Restart Claude Desktop
- Look for your server in Claude's interface
- Try using a simple tool to verify it's working
Best Practices
- Use Virtual Environments: Isolate dependencies for each MCP server
- Manage Secrets Securely: Use environment files or secret management tools
- Enable Debug Logging: During development to troubleshoot issues
- Organize Tools: Group related tools in separate servers
- Document Your Tools: Use clear descriptions and type annotations
Example: Complete Setup
Here's a complete example setting up a project with custom tools:
- Create your project structure:
my-mcp-project/
.env
requirements.txt
tools.py
- Create
tools.py:
from arcade_tdk import tool
from typing import Annotated
@tool
def greet(name: Annotated[str, "Name to greet"]) -> str:
"""Greet someone by name."""
return f"Hello, {name}!"
@tool
def calculate(
expression: Annotated[str, "Math expression"]
) -> Annotated[float, "Result"]:
"""Calculate a mathematical expression."""
return eval(expression, {"__builtins__": {}}, {})
- Configure Claude Desktop:
{
"mcp-servers": {
"my-project": {
"command": "python",
"args": ["-m", "arcade_mcp", "stdio", "--debug"],
"cwd": "/path/to/my-mcp-project"
}
}
}
- Restart Claude Desktop and your tools will be available!