Skip to main content
Glama
ynnekF

mcp-server

by ynnekF
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

Model Context Protocol (MCP) Server

The Model Context Protocol (MCP) Server is a server implementation that adheres to the Model Context Protocol. It is designed to facilitate communication between clients and models in a standardized way, enabling seamless integration and interaction.

Reference MCP Python SDK

This project aims to provide an example of a simple custom MCP server that can be used locally with tools like Copilot Chat. It demonstrates how to set up a server that can respond to requests and manage context information for clients.

Features

  • Context Management: The MCP Server manages context information for each client, allowing models to access relevant data and state information.

  • Protocol Compliance: The server strictly follows the MCP specifications, ensuring compatibility with other MCP-compliant clients and services.

  • Extensibility: The server is designed to be easily extensible, allowing developers to add new features and capabilities as needed.

Related MCP server: MCP Server Sample

Getting Started

To get started with the MCP Server, follow these steps:

Install UV Trying out UV instead of pip for this project: UV install methods

curl to download the script and pipe it to sh:

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

Add $HOME/.local/bin to your PATH:

$ source $HOME/.local/bin/env

Create a uv-managed project:

$ uv init .

Add MCP to the project dependencies:

$ uv add "mcp[cli]"

Test the MCP Server You can test the MCP Server by running the following command:

$ uv run mcp dev main.py

Run the MCP Server

For integration with Copilot Chat, we need to create .vscode/mcp.json in the project root with the following content to the servers section

"mcp-server": {
    "type": "stdio",
    "command": "<uvPath>",
    "args": [
        "run",
        "main.py"
    ]
}

Then you can add the MCP resource to Copilot chat.. after that Copilot will have access to the defined resources and tools.

Here is an example of Copilot interacting with the greeting tool.

Hello, Ken! 🎉

I can see your MCP server is working beautifully - it just provided me with a 
personalized greeting for you! It's fantastic to see your Model Context 
Protocol server in action, dynamically generating content based on context.

Your MCP server setup looks solid with UV package management, and it's clearly
functioning well if it's able to serve up dynamic greetings through the protocol. 
This is exactly the kind of extensible, context-aware functionality that makes MCP 
so powerful!

What would you like to explore or build next with your MCP server, Ken? Whether 
it's adding more dynamic resources, enhancing the greeting functionality, or 
working on other features, I'm here to help! 🚀

To run the MCP Server manually, use the following command:

// With Claude
$ uv run mcp install main

// Else
$ uv run main.py

API Reference

The MCP Server exposes a RESTful API for communication with clients. Refer to the API documentation for detailed information on available endpoints, request/response formats, and authentication requirements.

Contributing

Contributions to the MCP Server are welcome! If you would like to contribute, please follow these steps:

  1. Fork the repository.

  2. Create a new branch for your feature or bug fix.

  3. Make your changes and commit them with descriptive messages.

  4. Submit a pull request for review.

License

The MCP Server is licensed under the MIT License. See the LICENSE file for more information.

Available Tools

1 tool
addA

Add two numbers

ParametersJSON Schema
NameRequiredDescriptionDefault
aYes
bYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The operation is inherently transparent (simple addition). The description adds no beyond what the name implies, but for this elementary tool, that is adequate. No contradictions with missing annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (three words) and front-loaded with the essential information. Every word is meaningful with no wasted content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with clear inputs and an output schema likely defining the result. The description covers the core functionality completely for this trivial case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description 'Add two numbers' implies both parameters are the numbers to be added, providing minimal added meaning. The parameter types (integers) are already clear from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the action ('Add') and the resource ('two numbers'), leaving no ambiguity. The verb-resource combination is specific and sufficient for this simple arithmetic operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives, but given its simplicity and the absence of sibling tools, the implied usage is straightforward. However, it lacks any context-specific recommendations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev0.1.0
    • First observedadd
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools.

Naming Consistency5/5

With a single tool, naming is consistent and follows a clear pattern.

Tool Count1/5

A single tool for simple arithmetic is far too few for a meaningful server; it feels incomplete.

Completeness1/5

The server only provides addition, leaving all other math operations and potential use cases uncovered, which is severely incomplete.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ynnekF/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server