qbash Connectors / Wistia

Wistia MCP serverand Python AI tasks

qbash hosts a Wistia 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 Wistia with models such as Claude and GPT.

Connect Wistia free

Add the qbash MCP

Use Wistia from Claude Code, Codex, Cursor and other MCP clients. Connect Wistia in qbash, and your agent can work with its data and build Tasks that call it.

claude mcp add --transport http qbash https://mcp.qbash.com/mcp

Then run /mcp in Claude Code and sign in with qbash.

List the account's folders with media counts. Wistia's API called folders projects before its 2026-01 release
List the media in one folder, including its subfolders, with every field Wistia returns and each media's file versions (assets)
Get one media by its hashed_id, with the same fields and file versions (assets) as list_media
List a media's caption tracks, one per language, each with its full text in SRT format
Get one caption track of a media by language, with its SRT text and optionally its timed segments

Read the docs

Write a Wistia task in Python

A qbash Task is a Python function hosted in the cloud. Python is the runtime and defines the process, and built-in inline prompts run on leading models such as Claude, GPT, Gemini and Grok.

Run a Task on a schedule, from an HTTP request or when a connected app sends an event. Your agents and chat tools call it over MCP.

Each run is logged with its inputs and results, and you can turn data logging off for any Task. Every Task has version control, and each run is locked to the version it ran.

Write chapter titles from a video's captions

get_captions returns the English track with a start and end time for each caption. An inline prompt groups the captions into chapters and gives each one a title and a start time.

qbash Tasks Python AI SDK

main.py
captions = qbash.integrations.wistia.get_captions(
    media_id="g5pnf59ala",
    language="eng",
    include_segments=True,
)["captions"]
if captions["segments"]:
    chapters = qbash.ai.run_prompt(
        slug="wistia-chapter-titles",
        variables={"segments": captions["segments"]},
    )
    qbash.output(chapters)
else:
    qbash.output("The video's English caption track has no text yet.")

Sample get_captions response

{
  "status": "success",
  "captions": {
    "id": "tr8k2c1m9x",
    "media_id": "g5pnf59ala",
    "language": "eng",
    "english_name": "English",
    "native_name": "English",
    "text": "1\n00:00:00,000 --> 00:00:04,000\nThis walkthrough covers setting up a qbash workspace.\n\n2\n00:00:04,000 --> 00:00:09,500\nFirst, connect the tools your team already uses.\n\n3\n00:00:09,500 --> 00:00:15,000\nThen build a task that runs every morning.\n",
    "is_draft": false,
    "version": 2,
    "segments": [
      {
        "start_ms": 0,
        "end_ms": 4000,
        "text": "This walkthrough covers setting up a qbash workspace."
      },
      {
        "start_ms": 4000,
        "end_ms": 9500,
        "text": "First, connect the tools your team already uses."
      },
      {
        "start_ms": 9500,
        "end_ms": 15000,
        "text": "Then build a task that runs every morning."
      }
    ]
  }
}

Custom MCP server

Build a custom MCP server with Wistia

Create a hosted MCP server that combines Wistia tools with your other connectors, Tasks and memory folders. You choose each tool it exposes, so a server can share Wistia reads with write tools left off.

Share the server with your team, and each person adds it to the client they already use.

How permissions work Package an MCP server

How to set it up

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