what is openai-mcp-client?
openai-mcp-client is a client application that allows users to interact with their GitHub profile using AI-powered queries through the Model Context Protocol (MCP).
how to use openai-mcp-client?
To use openai-mcp-client, first install the MCP server for GitHub, configure your GitHub Personal Access Token, and then run the client application either in simple mode or integrated with OpenAI for advanced queries.
key features of openai-mcp-client?
- Integration with OpenAI for AI-powered GitHub queries
- Ability to run commands to interact with GitHub repositories
- Simple mode for basic tool calls
use cases of openai-mcp-client?
- Querying the number of commits in a specific repository.
- Automating repository management tasks like creating repositories, pushing changes, and making pull requests.
- Enhancing productivity by using AI to manage GitHub profiles.
FAQ from openai-mcp-client?
- Can I use openai-mcp-client without a GitHub account?
No, you need a GitHub account and a Personal Access Token to use this client.
- Is there a cost associated with using openai-mcp-client?
The client itself is free to use, but you may incur costs associated with GitHub usage depending on your account type.
- What programming language is openai-mcp-client written in?
openai-mcp-client is written in JavaScript.
openai-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."