qbash Connectors / GitHub

GitHub MCP serverand Python AI tasks

qbash hosts a GitHub MCP server you can use in Claude, ChatGPT, Codex, Cursor, Grok Bot and Muse.

Developers use qbash Tasks to write cloud-hosted Python functions that pair GitHub with models such as Claude and GPT.

MCP server

Build a GitHub MCP server

Give ChatGPT, Claude and your other AI tools access to GitHub through one server. You pick which GitHub tools it shares, and you can add other connectors, memory folders and Tasks to the same server.

How to set it up

Connect GitHub on the qbash Connectors page.
Create an MCP server and add the GitHub tools you want to share.
Paste the server URL into your client. It connects with OAuth or an access token.

Connect a client Package an MCP server

Python AI task

Write a GitHub task in Python

A qbash Task is a hosted Python function that calls GitHub and AI models.

Draft a weekly development update

Read seven days of commit messages and ask an inline prompt to group the changes into a reviewable draft.

main.py
since = (datetime.now(timezone.utc) - timedelta(days=7)).isoformat()
report = qbash.integrations.github.list_commits(
    owner="YOUR_ORGANIZATION", repo="YOUR_REPOSITORY",
    since=since, per_page=50, page=1,
)
if report["commits"]:
    draft = qbash.ai.run_prompt(
        slug="github-development-update",
        variables={"commits": json.dumps(report["commits"])},
    )
    qbash.output(draft)
else:
    qbash.output("No commits in this period.")

Sample list_commits response

{
  "status": "success",
  "commits": [
    {
      "sha": "abc123",
      "html_url": "https://github.com/example/repo/commit/abc123",
      "commit": {
        "message": "Add CSV export for reports",
        "author": {
          "name": "Sam",
          "date": "2026-09-28T12:00:00Z"
        }
      }
    }
  ],
  "count": 1
}

What the GitHub connector can do

Read files, commits and the diff between two branches or tags
Search code across your repositories
Review a pull request’s changed files, reviews and comments
Open, update, review and merge pull requests
Create, update, search and comment on issues
Check CI status and check runs for a commit or branch

See all 30 GitHub methods in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls GitHub, your other connectors and models such as Claude, GPT, Gemini and Grok. qbash hosts and runs it.

Run Tasks on a schedule or from your team's tools

+ more

Deterministic where it counts Write the logic in Python and call a model only for the steps that need judgement, so the rest runs the same way every time.
Version controlled Every save is a revision you can compare and roll back.
Logged Each run records its inputs, output, errors and what started it.
Shared credentials Connections belong to your organization, so a Task keeps working when its author is away.

qbash Tasks Python AI SDK

GitHub MCP questions

Does GitHub have an official MCP server?

Yes. GitHub maintains the open source github/github-mcp-server. qbash hosts its own GitHub server so a team can share GitHub tools next to other connectors and pick which tools each server exposes. The same calls run in Python tasks.

Which GitHub permissions does it ask for?

The OAuth app requests the repo and read:user scopes. Private repositories appear only when the authorization reaches them, and some organizations must approve the app first.

Can it push commits or edit files?

No. Write access covers pull requests, issues, reviews and comments, including merging a pull request. There is no method that commits to a branch.

Guides that use GitHub

Build a GitHub task

Write it in Python with AI steps, and qbash hosts it with versions and run logs.

Build a task

Build a GitHub MCP server

Pick the GitHub tools to share and connect ChatGPT, Claude or Grok Bot.

Build an MCP server

GitHub MCP serverand Python AI tasks