home / mcp / mcp multi-service agent mcp server

MCP Multi-Service Agent MCP Server

Provides weather, web search, HF inference provider information, and sentiment analysis via MCP servers.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "deon62-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp",
        "mcp",
        "run",
        "server.py"
      ],
      "env": {
        "ENV": "PLACEHOLDER"
      }
    }
  }
}

You can run a multi-service MCP server that exposes weather, web search, HF inference provider information, and sentiment analysis through a single, extensible platform. This setup lets you connect an AI agent, test tools in a debugger, and access a web UI for sentiment insights, all coordinated by a centralized MCP server.

How to use

To use this MCP server, start the server process locally, then launch your AI agent to discover and interact with the available tools. You can query weather for locations, perform web searches, fetch information about Hugging Face inference providers, and analyze sentiment through the Gradio interface. Interact with the agent to see tools listed and tested in real time.

How to install

Prerequisites: you need Python 3.10 or higher, the uv package manager, Node.js for the MCP inspector, and a Hugging Face account if you plan to use tiny-agents.

# 1. Clone the project and enter the directory
git clone https://github.com/Deon62/mcp.git
cd mcps

# 2. Install Python dependencies
uv pip install mcp[cli] requests

# 3. Install tiny-agents (if not already installed)
pip install tiny-agents

# 4. Install sentiment analysis dependencies
cd mcp-sentiment
python -m venv venv
venv\Scripts\activate  # On Windows
# source venv/bin/activate  # On Linux/Mac
pip install -r requirements.txt

Additional sections

Configuration and usage details are provided below to help you set up the agent and run the server. If you need debugging tooling, you can use the MCP Inspector to connect to the local server and test each tool individually.

Available tools

get_weather

Fetches weather information for a given location to answer questions like point-in-time forecasts or current conditions.

web_search

Performs web searches to retrieve information and summaries for user queries.

get_hf_inference_providers

Returns a comprehensive list of Hugging Face inference providers and deployment options.

sentiment_analysis

Analyzes text sentiment with polarity and subjectivity scores, and classifies as positive, negative, or neutral.