Ryan Malloy
997cf8dec4
Features: - FastMCP-based MCP server for Claude Code agent recommendations - Hierarchical agent architecture with 39 specialized agents - 10 MCP tools with enhanced LLM-friendly descriptions - Composed agent support with parent-child relationships - Project root configuration for focused recommendations - Smart agent recommendation engine with confidence scoring Server includes: - Core recommendation tools (recommend_agents, get_agent_content) - Project management tools (set/get/clear project roots) - Discovery tools (list_agents, server_stats) - Hierarchy navigation (get_sub_agents, get_parent_agent, get_agent_hierarchy) All tools properly annotated for calling LLM clarity with detailed arguments, return values, and usage examples.
38 lines
1.1 KiB
Python
38 lines
1.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Claude Agent Selection MCP Server - Production Entry Point
|
|
|
|
Built following FastMCP best practices:
|
|
- Single entry point with proper async handling
|
|
- Clean server initialization
|
|
- Full feature set with hierarchical agent intelligence
|
|
"""
|
|
|
|
from agent_mcp_server.server import mcp, initialize_server
|
|
|
|
async def initialize_and_run():
|
|
"""Initialize services and start server"""
|
|
await initialize_server()
|
|
# Use run() in synchronous context as per FastMCP best practices
|
|
await mcp.run_async(transport="stdio")
|
|
|
|
def main():
|
|
"""
|
|
Main entry point following FastMCP best practices.
|
|
Initializes then uses mcp.run() in synchronous context.
|
|
"""
|
|
# Import here to avoid any import-time async issues
|
|
import asyncio
|
|
|
|
# Use the recommended pattern from FastMCP docs
|
|
async def init_then_run():
|
|
await initialize_server()
|
|
|
|
# Run initialization
|
|
asyncio.run(init_then_run())
|
|
|
|
# Then run the server synchronously as recommended
|
|
mcp.run(transport="stdio")
|
|
|
|
if __name__ == "__main__":
|
|
main() |