Context4
Context4MCP connector / BETA

GitHub MCP connector

Review GitHub issues, pull requests and checks with AI.

Start with your task

GitHub — in your AI.
Start with one task.

Copy the prompt for your AI. You will confirm the account connection and access permission separately.

What you can ask AI to do ↓

Your data. Your tasks.

What to ask AI to do in GitHub

Start with one clear task. These examples use the current connector's tools; results depend on your account data and permissions.

01

Review issues

«Retrieve the issues in this GitHub repository and help prioritize them.»

AI will request the issue list and help review it.

02

Review a pull request

«Prepare an overview of this GitHub pull request.»

AI will retrieve a pull request overview and help explain the changes.

03

Investigate a failed check

«Show the failed jobs in this GitHub Actions run.»

AI can review information about unsuccessful jobs.

From prompt to first task

How to connect GitHub to AI

  1. 01

    Copy the prompt

    Choose an AI client in the setup block. Paste the prompt into your chat and send it: it explains how to configure Context4 and find the service you need.

  2. 02

    Connect your account

    Sign in to Context4, then sign in to GitHub and confirm access in your browser.

  3. 03

    Assign your first task

    Start by reading data from GitHub. AI will check the available tools and connection, then perform a suitable request if possible.

For ChatGPT, you need to add an HTTPS-accessible MCP server manually. Connection availability depends on your account and workspace settings. ChatGPT guide →

Your account.
Your permissions.

Context4 gives AI tools to work with GitHub. Data and actions are available within the connected account's permissions.

AI may receive an empty response or an access error. To make changes, it needs an appropriate tool, parameters and your instruction.

How connections and authorization work →Context4: GitHub MCP connector, an AI request and available actions

Before you connect

Questions about GitHub and MCP

What does the GitHub MCP connector provide?

It gives your AI tools for interacting with GitHub. Review GitHub issues, pull requests and checks with AI. Available actions depend on the connector implementation and the connected account's permissions. Learn more about how MCP works in Context4.

What tasks can I assign to AI in GitHub?

For example: review issues, review a pull request, investigate a failed check. Example requests appear above. The answer is based on data returned by the service; missing data or insufficient permissions may prevent a result.

What do I need to connect GitHub?

An account in GitHub, permission to access the required data and an AI client that supports MCP. GitHub uses OAuth 2.0: you sign in and confirm access in your browser. Details are in our service connection guide.

Can I connect GitHub to my AI?

The setup guide has separate paths for ChatGPT, Claude, Codex, Claude Code, Hermes and OpenClaw. ChatGPT needs a plugin; Codex can connect MCP directly. The prompt explains the steps, but does not automatically install a missing plugin. Access depends on client capabilities and your account permissions. End-to-end compatibility of Hermes and OpenClaw with Context4 has not yet been verified.

Can AI change data in GitHub?

Only if the connector provides the relevant tool and it is available to your connection. Explicitly request creation, changes or sending: specify the object and required action. Check the result afterwards. Connectors do not all support the same operations.

How do I disconnect access to GitHub?

Disconnect the account in Context4 and revoke the permission or key in the settings of GitHub. Do not paste passwords or secret keys into a regular AI chat. Learn more about access management.

How much does using GitHub through Context4 cost?

Context4 is free. See the terms of use or support. Subscriptions to GitHub and the AI client may be billed separately under each service's rules.

Technical reference GitHub

Version 1.1.0 · beta · 24 actions in the catalog. Permissions and availability are checked when connecting.

MCP connector actions

  • Comment on an issue or pull request

    issue.comment

  • List issue comments

    issue.comments

  • Create an issue

    issue.create

  • Get an issue

    issue.get

  • List issues

    issue.list

  • Update or close an issue

    issue.update

  • List check runs of a ref

    pull.checks

  • Open a pull request

    pull.create

  • List files of a pull request

    pull.files

  • Get a pull request

    pull.get

  • List pull requests

    pull.list

  • Merge a pull request

    pull.merge

  • Get a pull request with files and reviews

    pull.overview

  • Submit a review

    pull.review

  • List reviews of a pull request

    pull.reviews

  • Compare two refs

    repository.compare

  • Get a repository

    repository.get

  • Get the failed jobs of a workflow run

    run.failed_jobs

  • Get a workflow run

    run.get

  • List jobs of a workflow run

    run.jobs

  • List workflow runs

    run.list

  • Re-run the failed jobs of a run

    run.rerun_failed

  • Search code

    search.code

  • Search issues and pull requests

    search.issues

Data and authorization

Authorization: OAuth 2.0.

    No synchronized data types are claimed.