qbash Connectors / X (Twitter)

X (Twitter) MCP serverand Python AI tasks

qbash hosts a X (Twitter) 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 X (Twitter) with models such as Claude and GPT.

Connect X (Twitter) free

MCP server

Build a X (Twitter) MCP server

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

How to set it up

Connect X (Twitter) on the qbash Connectors page.
Create an MCP server and add the X (Twitter) 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 X (Twitter) task in Python

A qbash Task is a hosted Python function that calls X (Twitter) and AI models.

Review recent product mentions

Search for a product name and ask an inline prompt to group questions, complaints, and praise with post links.

main.py
report = qbash.integrations.x.search(
    query='"YourProduct" -is:retweet lang:en',
    max_results=25,
)
posts = report.get("tweets", [])
if posts:
    review = qbash.ai.run_prompt(
        slug="product-mentions",
        variables={"posts": json.dumps(posts)},
    )
    qbash.output(review)
else:
    qbash.output("No recent matching posts were returned.")

Sample search response

{
  "tweets": [
    {
      "id": "123",
      "text": "Does YourProduct support scheduled exports?",
      "author_username": "customer",
      "author_name": "Customer",
      "created_at": "2026-09-29T12:00:00Z",
      "retweet_count": 0,
      "like_count": 2,
      "reply_count": 1,
      "url": "https://x.com/customer/status/123"
    }
  ],
  "result_count": 1
}

What the X (Twitter) connector can do

Return the authenticated user's profile (requires OAuth user context)
Publish a new tweet (requires OAuth user context)
Upload a stored image, GIF or video to X and return a media_id for create_tweet
Check whether X has finished processing an uploaded media id
Look up a public user profile by username
Fetch a single tweet with public engagement metrics
Fetch a tweet with extended metrics including non_public_metrics and organic_metrics for tweets authored by the authenticated user
List recent tweets from a user by their numeric user ID
Search recent posts on X using the X API v2
Fetch recent @mentions of a user by username
Get recent tweet volume counts for a search query
Fetch recent posts from a user's timeline by username
Get trending topics for a location by WOEID

See every X (Twitter) method in the SDK Reference

qbash Tasks: AI applications in Python

A Task is a Python function that calls X (Twitter), 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

X (Twitter) MCP questions

Does X have an official MCP server?

Yes. X publishes XMCP, an open-source server at github.com/xdevplatform/xmcp that turns X API endpoints into tools. qbash hosts its own X server, which can share one URL with your other connectors and the same calls your Python tasks make.