Skip to main content
Glama

MCP Server Example

This repository contains an implementation of a Model Context Protocol (MCP) server for educational purposes. This code demonstrates how to build a functional MCP server that can integrate with various LLM clients.

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications - it provides a standardized way to connect AI models to different data sources and tools.

MCP Diagram

Key Benefits

  • A growing list of pre-built integrations that your LLM can directly plug into

  • Flexibility to switch between LLM providers and vendors

  • Best practices for securing your data within your infrastructure

Related MCP server: MCP Tool

Architecture Overview

MCP follows a client-server architecture where a host application can connect to multiple servers:

  • MCP Hosts: Programs like Claude Desktop, IDEs, or AI tools that want to access data through MCP

  • MCP Clients: Protocol clients that maintain 1:1 connections with servers

  • MCP Servers: Lightweight programs that expose specific capabilities through the standardized Model Context Protocol

  • Data Sources: Both local (files, databases) and remote services (APIs) that MCP servers can access

Core MCP Concepts

MCP servers can provide three main types of capabilities:

  • Resources: File-like data that can be read by clients (like API responses or file contents)

  • Tools: Functions that can be called by the LLM (with user approval)

  • Prompts: Pre-written templates that help users accomplish specific tasks

System Requirements

  • Python 3.10 or higher

  • MCP SDK 1.2.0 or higher

  • uv package manager

Getting Started

Installing uv Package Manager

On Windows:

powershell -ExecutionPolicy Bypass -c "irm https://astral.sh/uv/install.ps1 | iex"

On MacOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Make sure to restart your terminal afterwards to ensure that the uv command gets picked up.

Project Setup

  1. Create and initialize the project:

# Create a new directory for our project
uv init mcp-server
cd mcp-server

# Create virtual environment and activate it
uv venv
.venv\Scripts\activate  # On Windows use: source .venv/bin/activate

# Install dependencies
uv add "mcp[cli]" httpx
  1. Create the server implementation file main.py

Running the Server

  1. Start the MCP server:

uv run main.py
  1. The server will start and be ready to accept connections

Connecting to Claude Desktop

  1. Install Claude Desktop from the official website

  2. Configure Claude Desktop to use your MCP server:

Edit claude_desktop_config.json:

{
    "mcpServers": {
        "mcp-server": {
            "command": "uv",  # It's better to use the absolute path to the uv command
            "args": [
                "--directory",
                "/ABSOLUTE/PATH/TO/YOUR/mcp-server",
                "run",
                "main.py"
            ]
        }
    }
}
  1. Restart Claude Desktop

Troubleshooting

If your server isn't being picked up by Claude Desktop:

  1. Check the configuration file path and permissions

  2. Verify the absolute path in the configuration is correct

  3. Ensure uv is properly installed and accessible

  4. Check Claude Desktop logs for any error messages

Available Tools

1 tool
get_documentationA
Search for and retrieve documentation from LlamaIndex or LangChain sites.

This tool searches for relevant documentation using Serper API and then scrapes
the content from the top results to provide comprehensive information.

Args:
    query: Search query for documentation (e.g., "vector store", "chat models", "retrieval")
    library: The library to search for ('llamaindex' or 'langchain')
    max_results: Maximum number of documentation pages to retrieve (1-2, default 2)

Returns:
    Formatted documentation content from the search results

Inputs: query (required), library (required), max_results. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusing it with others. The tool's purpose is clearly defined and distinct.

    Naming Consistency5/5

    The single tool follows a consistent verb_noun pattern (get_documentation). Consistency is trivially maintained with one tool.

    Tool Count3/5

    A single tool feels thin for a server, even if the tool is comprehensive. The server lacks the breadth typical of a well-scoped integration, making it borderline.

    Completeness5/5

    The tool fully covers its stated domain of retrieving documentation from LlamaIndex or LangChain. It provides appropriate parameters and returns comprehensive content, with no obvious gaps for a read-only documentation tool.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      A demonstration MCP server for local development and testing with Claude Desktop on WSL. Provides basic utility tools including greeting messages, echo functionality, and server information retrieval.
      3
      MIT