Skip to main content
Glama
deenesjakoruzh
suspicious-cow

Model Context Protocol (MCP) Server

by suspicious-cow
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Model Context Protocol (MCP) Python Implementation

This project implements a functioning Model Context Protocol (MCP) server and client in Python, following the Anthropic MCP specification. It demonstrates the key patterns of the MCP protocol through a simple, interactive example.

What is MCP?

The Model Context Protocol (MCP) is an open standard built on JSON-RPC 2.0 for connecting AI models to external data sources and tools. It defines a client-server architecture where an AI application communicates with one or more MCP servers, each exposing capabilities such as:

  • Tools: Executable functions that perform actions

  • Resources: Data sources that provide information

  • Prompts: Predefined templates or workflows

MCP standardizes how these capabilities are discovered and invoked, serving as a "USB-C for AI" that allows models to interact with external systems in a structured way.

Related MCP server: simple_mcp

Project Structure

  • server/: MCP server implementation

    • server.py: WebSocket server that handles MCP requests and provides sample tools/resources

  • client/: MCP client implementation

    • client.py: Demo client that connects to the server and exercises all MCP capabilities

Features Demonstrated

This implementation showcases the core MCP protocol flow:

  1. Capability Negotiation: Client-server handshake via initialize

  2. Capability Discovery: Listing available tools and resources

  3. Tool Invocation: Calling the add_numbers tool with parameters

  4. Resource Access: Reading text content from a resource

Setup

  1. Create a virtual environment:

    python3 -m venv .venv
source .venv/bin/activate

  2. Install dependencies:

    pip install -r requirements.txt

Usage

  1. Start the MCP server (in one terminal):

    python server/server.py

  2. Run the MCP client (in another terminal):

    python client/client.py

The client will connect to the server, perform the MCP handshake, discover capabilities, and demonstrate invoking tools and accessing resources with formatted output.

How It Works

MCP Server

The server:

  • Accepts WebSocket connections

  • Responds to JSON-RPC requests following the MCP specification

  • Provides a sample tool (add_numbers)

  • Provides a sample resource (example.txt)

  • Supports the MCP handshake and capability discovery

MCP Client

The client:

  • Connects to the server via WebSocket

  • Performs the MCP handshake

  • Discovers available tools and resources

  • Demonstrates calling a tool and reading a resource

  • Presents the results in a formatted display

Protocol Details

MCP implements these key methods:

Method

Description

initialize

Handshake to establish capabilities

tools/list

List available tools

tools/call

Call a tool with arguments

resources/list

List available resources

resources/read

Read resource content

prompts/list

List available prompts

Extending the Project

You can extend this implementation by:

  • Adding more tools with different capabilities

  • Adding dynamic resources that change on each read

  • Implementing prompt templates for guided interactions

  • Creating more interactive client applications

References

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

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Agent Construct

    ai-mcp-garage
    A
    license
    Not graded
    quality
    Not graded
    maintenance
    An MCP server implementation that standardizes how AI applications access tools and context, providing a central hub that manages tool discovery, execution, and context management with a simplified configuration system.
    13
    -

  • MCP Server

    imanelmzk
    F
    license
    Not graded
    quality
    F
    maintenance
    A basic MCP server implementation using Node.js and TypeScript that bridges AI models with external tools and data sources via JSON-RPC.
    2
    -

  • mcp-intro

    Hugol4ka
    F
    license
    Not graded
    quality
    B
    maintenance
    A demo MCP server that connects an AI to external systems by exposing Python functions as tools and data as resources, using the stdio transport.
    -