Skip to main content
Glama
rawanosama14

mcp-ai-agent

by rawanosama14
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

⚡ Minimal MCP AI Agent with Embedded Testing UI

A clean, single-file implementation of a Model Context Protocol (MCP) AI Agent powered by Groq (openai/gpt-oss-120b), LangChain, and FastAPI, featuring an embedded dark-mode testing UI[cite: 13].

✨ Features

  • Built-in MCP Tools:

    • analyze_text: Analyzes text word/character count and sentiment indicators[cite: 13].

    • get_system_info: Tracks real-time system metrics (CPU usage, memory consumption, and uptime using psutil)[cite: 13].

  • LangChain Tool Calling: The agent autonomously decides when and how to execute tools based on user queries[cite: 13].

  • Embedded Web UI: A modern sidebar interface to test queries, view tool execution logs, and monitor live status[cite: 13].

Related MCP server: System Monitor MCP Server

🛠️ Tech Stack

  • Backend: FastAPI, Uvicorn, Python[cite: 13]

  • AI / LLM: LangChain, Groq API (openai/gpt-oss-120b)[cite: 13]

  • System Monitoring: psutil[cite: 13]

  • Frontend: Embedded HTML/CSS (Dark theme UI)[cite: 13]

🚀 Quick Start

  1. Clone the repository:

    git clone [https://github.com/rawanosama14/mcp-groq-ai-agent.git](https://github.com/rawanosama14/mcp-groq-ai-agent.git)
cd mcp-groq-ai-agent

2. **Install dependencies:**
```bash
pip install fastapi uvicorn langchain-groq langchain-core psutil pydantic

  1. Run the server:

python server.py

  1. Open the UI: Navigate to http://127.0.0.1:8000 in your browser to interact with the agent.

Powered by Groq & FastAPI 🚀

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP System Monitor Server

    huhabla
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables real-time monitoring of system resources including CPU, GPU (NVIDIA, Apple Silicon, AMD/Intel), memory, disk, network, and processes across Windows, macOS, and Linux platforms through natural language queries.
    3
    MIT

  • open-monitor

    hasna
    A
    license
    Not graded
    quality
    F
    maintenance
    Multi-machine system monitor with a built-in MCP server that enables AI agents to query health metrics, manage processes, schedule cron jobs, and run diagnostics across local and remote machines.
    133 npm
    Apache 2.0