README.md
Provides tools for managing todo lists, weather, and user information.
🤖MCP
Core Capabilities:
- 🌦️ Weather: Provides current atmospheric conditions for any location.
- ⏰ System Time: Syncs the agent with the exact local system clock.
- 👤 Contextual Awareness: Accesses local user information to personalize AI responses.
- 🔌 Universal Connectivity: Fully compatible with any MCP client (Cursor, Claude Desktop, etc.).
Running the MCP server
To start the MCP server locally:
npm run mcp
Agent_B1997 helps you to connecting & testing MCP.
...
Setup with Claude Desktop (Local)
... (existing local config) ...
🌐 Local Deployment (API)
Once you start the project using npm run dev, you can access the Agent UI & API locally.
1. Local API Endpoints
- MCP Gateway:
http://localhost:3000/api/mcp(MCP JSON-RPC)
Example MCP Tool List:
curl -X POST http://localhost:3000/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}'
Tools (3)
get_weatherProvides current atmospheric conditions for any location.get_system_timeSyncs the agent with the exact local system clock.get_user_contextAccesses local user information to personalize AI responses.Configuration
claude_desktop_config.json
{"mcpServers": {"gemini-agent": {"command": "npm", "args": ["run", "mcp"], "cwd": "/path/to/gemini-agent"}}}Try it
→What is the current weather in Tokyo?
→What time is it on my local system right now?
→Can you provide my user profile information to help personalize your responses?
→Check the weather in London and tell me if I need an umbrella.