GitHub MCP Server

GitHub MCP Server

Enables AI agents to interact with GitHub repositories, issues, pull requests, code, and more through a comprehensive set of tools.

Category
访问服务器

README

GitHub MCP Free Hosting Showcase

This repository serves as a showcase to demonstrate how incredibly simple and fast it is to deploy an MCP server on Vinkius Cloud.

Built using the powerful @mcpfusion/core framework, this project illustrates the modern approach to creating secure, edge-native MCP servers with zero friction.

🚀 Ready to use? If you just want to add GitHub tools to your AI agent immediately, you can use the hosted version here:
👉 vinkius.com/mcp/github

About Vinkius Cloud

Vinkius Cloud is the premier platform for deploying MCP (Model Context Protocol) servers. It provides an enterprise-grade execution environment designed for performance, security, and developer experience.

  • Edge-Native Architecture: Your MCP servers run inside V8 isolate sandboxes globally, delivering sub-40ms cold starts.
  • Secure by Default: Built-in DLP (Data Loss Prevention) redaction, Ed25519 signed audit chains, and an instant kill switch.
  • Zero Friction Deployment: No complex DevOps required. You can deploy your MCP tools to production in seconds.
  • Massive Ecosystem: Powering over 4,000+ MCP servers in production, including integrations with Salesforce, Stripe, Slack, OpenAI, and more.

Available Tools

This GitHub MCP server exposes a comprehensive suite of tools for AI agents to interact with GitHub seamlessly:

  • Repositories
    • list_user_repositories: Retrieves all public repositories for a specific user.
    • list_org_repositories: Retrieves all repositories belonging to an organization.
    • get_repository_details: Fetches detailed configuration and attributes.
    • search_github_repositories: Finds repositories matching a search query.
  • Issues & Pull Requests
    • list_repo_issues: Retrieves issues for a specific repository.
    • get_issue_details: Fetches full issue details including comments and assignees.
    • create_new_issue: Opens a new issue.
    • add_issue_comment: Posts a new comment on an existing issue or PR.
    • list_pull_requests: Retrieves pull requests.
    • create_pull_request: Opens a new pull request.
  • Code & History
    • get_file_contents: Retrieves the contents of a file or directory.
    • search_github_code: Finds specific code snippets across GitHub.
    • list_branches: Returns all branches with their latest commit SHA.
    • list_commits: Returns commit history, optionally filtered by branch or SHA.
    • list_releases: Returns published releases, tags, and assets.
  • Users & Social
    • get_my_github_profile: Retrieves metadata for the authenticated user.
    • list_stargazers: Returns users who have starred a repository.
  • System
    • verify_api_connection: Checks GitHub API connectivity.

Deployment

To deploy this MCP Server to Vinkius Edge infrastructure, run:

npm run deploy

(This executes mcpfusion deploy under the hood)

Development

  1. Install dependencies:

    npm install
    
  2. Run the development server:

    npm run dev
    

About MCP Fusion

MCP Fusion is the TypeScript framework for secure MCP servers. It enforces security at the architectural level, ensuring raw data never reaches an LLM without passing through a typed egress firewall.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选