GitHub Repo Assistant MCP Server
Enables creating GitHub repositories under a fixed owner and pushing multiple files in a single commit via the Git Data API, designed for deployment as a Vercel serverless function.
README
GitHub Repo Assistant (MCP server)
An MCP server with two tools:
- create_repo — creates a GitHub repo under a fixed owner if it doesn't already exist
- push_files — creates/updates one or more files in a single commit (creates the branch if needed)
Designed to run as a Vercel serverless function so Claude can call it as a remote MCP connector.
1. Push this code to GitHub
cd github-repo-assistant-mcp
git init
git add .
git commit -m "Initial commit: github repo assistant MCP server"
git branch -M main
git remote add origin https://github.com/<your-username>/github-repo-assistant-mcp.git
git push -u origin main
2. Deploy to Vercel
-
Go to https://vercel.com/new and import the GitHub repo you just pushed.
-
Leave build settings as default (no build step needed — it's a single API route).
-
Before deploying (or right after, then redeploy), add these Environment Variables in the Vercel project settings:
Name Value GITHUB_TOKENA GitHub Personal Access Token with reposcope (fine-grained: Contents + Administration read/write)GITHUB_OWNERYour GitHub username or org name — the account repos will be created under -
Deploy. Your MCP endpoint will be:
https://<your-project-name>.vercel.app/api/mcp
3. Connect it to Claude
Add it as a custom connector using that URL. Once connected, you can ask Claude things like:
"Create a repo called
weekend-projectand push a basic Express server to it."
Claude will call create_repo then push_files against your GitHub account.
Creating a GitHub token
- GitHub → Settings → Developer settings → Personal access tokens → Fine-grained tokens
- Repository access: "All repositories" (or select ones, but then new repos can't be created into arbitrary names — "All repositories" is simpler for this use case)
- Permissions needed: Contents: Read and write, Administration: Read and write (Administration is required to create new repos)
Notes
- This server is stateless — each tool call is an independent request to the GitHub REST/Git Data API, which fits Vercel's serverless model well.
push_filesuses the Git Data API (trees/commits/refs) so multiple files land in a single commit rather than one API call per file.- All repos are created under the single
GITHUB_OWNERconfigured via environment variable. If you want Claude to create repos under different owners/orgs per request, add an optionalownerparameter to the tools and pass it through instead of reading fromprocess.env.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。