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>
1.9 KiB
1.9 KiB
02 - Building Apps
Build and run an MCP server programmatically using the FastAPI-like MCPApp interface.
Running the Example
- Run HTTP:
python examples/02_building_apps.py - Run stdio:
python examples/02_building_apps.py stdio
Source Code
--8<-- "docs/examples/02_building_apps.py"
MCPApp Features
1. Creating an App
from arcade_mcp_server import MCPApp
app = MCPApp(
name="my_server",
version="1.0.0",
title="My MCP Server",
instructions="This server provides utility tools",
log_level="INFO"
)
2. Adding Tools
Use the @app.tool decorator to add tools:
@app.tool
def my_tool(param: Annotated[str, "Description"]) -> str:
"""Tool description."""
return f"Result: {param}"
3. Running the Server
# Default HTTP transport
app.run()
# Specify options
app.run(
host="0.0.0.0",
port=8080,
reload=True, # Auto-reload on code changes
transport="http"
)
# For stdio transport (Claude Desktop)
app.run(transport="stdio")
4. Using Context
Tools can access runtime context:
@app.tool
async def context_aware(context: Context, value: str) -> dict:
"""Tool that uses context features."""
# Access user info
user_id = context.user_id
# Use MCP features if available
if context:
await context.log.info(f"Processing for user: {user_id}")
# Access secrets
secret_keys = list(context.secrets.keys())
return {
"user": user_id,
"value": value,
"available_secrets": secret_keys
}
Key Concepts
- FastAPI-like Interface: Familiar decorator-based API design
- Programmatic Control: Build servers without CLI dependency
- Transport Flexibility: Support for both HTTP and stdio transports
- Context Integration: Access to user info, logging, and secrets
- Development Features: Hot reload, debug logging, and more