Skip to main content
Glama
Utkarsh-kumar-singh

GitHub MCP Server

by Utkarsh-kumar-singh
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

🚀 GitHub MCP Server

A production-ready Model Context Protocol (MCP) Server built with Python that enables AI assistants and MCP clients to interact with GitHub repositories through the GitHub REST API.

This project demonstrates how to build a custom MCP server capable of performing GitHub operations such as listing repositories, retrieving repository information, managing issues, and extending to pull requests, workflows, and code management.

📌 Features

Repository Management

  • List all repositories for the authenticated user

  • Retrieve repository details

  • Access repository metadata

Issue Management

  • List repository issues

  • Create new issues

  • Close existing issues (future enhancement)

MCP Integration

  • Built using the official MCP Python SDK

  • Compatible with MCP Inspector

  • JSON-RPC based communication

  • Local STDIO transport support

Related MCP server: GitBridge

🏗️ Architecture

┌─────────────────────┐
│   MCP Client        │
│ (Inspector / AI)    │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   GitHub MCP Server │
│      (Python)       │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   GitHub REST API   │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   GitHub Account    │
└─────────────────────┘

📂 Project Structure

github-mcp/
│
├── server.py
├── .env
├── pyproject.toml
├── uv.lock
├── .gitignore
└── README.md

⚙️ Prerequisites

  • Python 3.10+

  • UV Package Manager

  • GitHub Account

  • GitHub Personal Access Token (PAT)

  • Node.js (for MCP Inspector)

🔑 GitHub Token Setup

Generate a Personal Access Token from:

https://github.com/settings/tokens

Recommended permissions:

Repository Access
Issues: Read & Write
Contents: Read
Pull Requests: Read & Write

Create a .env file:

GITHUB_TOKEN=your_github_token_here

📦 Installation

Clone the repository:

git clone <repository-url>
cd github-mcp

Initialize project:

uv init

Install dependencies:

uv add mcp requests python-dotenv

▶️ Running the Server

Start the MCP server:

uv run server.py

The server will wait for MCP client connections.

🔍 Using MCP Inspector

Start MCP Inspector:

npx @modelcontextprotocol/inspector

Open:

http://localhost:6274

Connection Settings:

Transport : STDIO

Command:
uv

Arguments:
run server.py

Click Connect.

🛠️ Available Tools

list_repositories

Returns all repositories accessible by the authenticated user.

Example

{}

Response

[
  {
    "name": "github-mcp",
    "full_name": "username/github-mcp",
    "private": false
  }
]

get_repository

Returns details for a specific repository.

Input

{
  "owner": "username",
  "repo": "github-mcp"
}

Response

{
  "name": "github-mcp",
  "description": "GitHub MCP Server",
  "stars": 10,
  "forks": 2
}

🔄 MCP Request Flow

User
 │
 ▼
MCP Client
 │
 ▼
Tool Call
 │
 ▼
GitHub MCP Server
 │
 ▼
GitHub REST API
 │
 ▼
Response Returned

🚧 Planned Enhancements

  • Create GitHub Issues

  • Close Issues

  • Pull Request Management

  • Branch Management

  • File Operations

  • GitHub Actions Integration

  • Repository Search

  • Code Search

  • OAuth Authentication

  • Remote MCP Deployment

🧠 Learning Outcomes

This project demonstrates:

  • Model Context Protocol (MCP)

  • MCP Tools

  • JSON-RPC Communication

  • GitHub REST API Integration

  • Authentication using PAT

  • MCP Inspector Usage

  • Production MCP Architecture

  • Local MCP Server Development

📄 License

MIT License

👨‍💻 Author

Built as a learning and production-ready MCP project for understanding MCP architecture, GitHub integrations, and AI tooling ecosystems.

Test commit for pull request

Available Tools

2 tools
get_repositoryD

Get details of a repository.

ParametersJSON Schema
NameRequiredDescriptionDefault
ownerYes
repoYes

TDQS

D1.8/5.0
Behavior1/5

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

No behavioral traits are disclosed. The description does not mention permissions, rate limits, or what 'details' entails. With no annotations provided, the description carries the full burden but fails to offer any transparency about side effects or prerequisites.

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

Conciseness2/5

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

The description is extremely concise but at the cost of informativeness. It consists of a single sentence that provides minimal value. Under-specification does not count as effective conciseness.

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

Completeness1/5

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

Given the lack of annotations, no output schema, and zero schema description coverage, the description is wholly inadequate. It does not convey enough information for an agent to use the tool correctly or understand its behavior.

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

Parameters1/5

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

Schema description coverage is 0% and the description adds no meaning to the parameters. The owner and repo parameters are not explained beyond their names, leaving their semantics implicit and ambiguous for an agent unfamiliar with GitHub conventions.

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

Purpose3/5

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

The description states 'Get details of a repository,' which is a clear verb+resource. However, it is somewhat vague as 'details' is not specific, and it does not distinguish from the sibling tool 'list_repositories' which likely lists repositories rather than getting a single one, but the distinction is only implicit.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention that this tool is for a specific repository identified by owner and repo, nor does it exclude use cases that would be better served by list_repositories.

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

list_repositoriesA

List all repositories of the authenticated user.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description must convey behavior. It implies a read-only operation by 'list', but does not confirm safety explicitly, nor disclose any side effects, rate limits, or pagination. Adequate for a simple 0-parameter tool.

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

Conciseness4/5

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

The description is a single, clear sentence with no wasted words. It is front-loaded with the key action.

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

Completeness3/5

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

The tool is simple with no parameters and no output schema, but the description does not specify what information is returned (e.g., names only or full details). This leaves some ambiguity for an agent.

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

Parameters4/5

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

There are no parameters, so the description has no burden. The schema coverage is 100% (trivially), and the description correctly omits parameter info.

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?

The description clearly states the verb 'list', the resource 'repositories', and the scope 'of the authenticated user', distinguishing it from the sibling tool 'get_repository' which likely fetches a single repository.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like 'get_repository'. There is no mention of context or exclusion criteria.

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. 2 tool updatesv0.1.0
    • First observedget_repository
    • First observedlist_repositories
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.5/5.0
Disambiguation5/5

The two tools are clearly distinct: one retrieves details of a specific repository, the other lists all repositories. No overlap in purpose.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern ('get_repository', 'list_repositories'), with appropriate singular/plural usage.

Tool Count1/5

With only 2 tools, the server is extremely limited for a GitHub-related service. Typical functionality requires many more tools (issues, PRs, etc.).

Completeness1/5

The tool surface is severely incomplete; it lacks any operations related to issues, pull requests, commits, content, or repository management beyond basic retrieval.

Maintenance

ActivityStale
ResponsivenessUnresponsive

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

  • GitHub MCP Server

    pipseedai
    A
    license
    A
    quality
    Not graded
    maintenance
    Enables AI agents to interact with GitHub repositories through the GitHub REST API for managing files, issues, and repository metadata. It supports both read operations like searching code and write operations such as creating repositories and updating issue comments.
    9
    -

  • git-mcp

    rkjavait
    F
    license
    B
    quality
    C
    maintenance
    Enables AI clients to interact with GitHub repositories, issues, pull requests, and code search through the GitHub REST API.
    12
    -

  • GitHub MCP Server

    Yash-R09
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to interact with GitHub through the GitHub REST API, supporting repository, file, issue, pull request, branch, commit, search, and label operations with explicit confirmation for write operations.
    -

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/Utkarsh-kumar-singh/MCP-INTEGRATION-GitHub'

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