About openai-mcp-client
An OpenAI MCP client that interacts with GitHub through the GitHub MCP server. Supports simple mode for direct tool calls and AI mode for natural language queries via OpenAI.
Key features
- 01GitHub MCP server integration
- 02OpenAI natural language queries
- 03Simple and AI operation modes
- 04GitHub repository management
- 05Automated workflow execution
Use cases
- 01Managing GitHub repositories via natural language
- 02Automating code commits and pull requests
- 03AI-assisted development workflows
- 04Querying commit history and code analysis
MCP support
The client connects to the GitHub MCP server via stdio transport to invoke tools.
Details
From the project READMEopenai-mcp-client
- Install mcp server for GitHub:
npm install -g @modelcontextprotocol/server-github
You need to configure two variables:
- Generate a GitHub Personal Access Token
- Get path to the MCP server executable (used for StdioClientTransport command):
which mcp-server-github
You can run the app on simple mode, which will call a single tool from GitHub MCP Server:
node client.js
Or you can integrate it with OpenAI and it allows you to interact with your GitHub profile through AI-powered queries. Examples below:
Example 1:
node client-with-openai.js "How many commits does my openai-mcp-client repo have that is under my username leartbeqiraj1?"
Example 2:
node client-with-openai.js "Please do the following: * make a simple html page. * create a repository called 'openai-created-this-repo'. * Push the html page to the 'openai-created-this-repo' repository. * Add a little css to the html page and then push it up. * Make an issue suggesting we add some more content on the html page. * Now make a branch called feature and make that fix and push the change. * Make a pull request against main with these changes."
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.