Google Meet MCP serverand Python AI tasks
qbash hosts a Google Meet 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 Google Meet with models such as Claude and GPT.
Add the qbash MCP
Use Google Meet from Claude Code, Codex, Cursor and other MCP clients. Connect Google Meet 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.
- Create a meeting room and get its join link. Optionally turn on auto recording, transcripts, or notes, and add members
- Get a meeting room's join link, settings, and the call in progress, by meeting code or link
- Change a meeting room's settings. Only rooms created with create_meeting can be changed
- End the call running in a meeting room for everyone. Only rooms created with create_meeting can be ended
- List the people who can join a meeting room without knocking
- Let people join a meeting room without knocking. Only rooms created with create_meeting can be changed
Write a Google Meet 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 up a call from its transcript
Read the transcript of a finished call, then ask an inline prompt for the decisions made and each action item with its owner.
transcript = qbash.integrations.google_meet.get_transcript_text(
conference_id=qbash.inputs.get("conference_id"),
include_speaker_names=True,
)
if transcript.get("entries"):
notes = qbash.ai.run_prompt(
slug="google-meet-call-notes",
variables={"transcript": transcript["text"]},
)
qbash.output({"transcript_id": transcript["transcript_id"], "notes": notes})
else:
qbash.output("This call has no transcript.")
Sample get_transcript_text response
{
"status": "success",
"transcript_id": "conferenceRecords/qbash-call-1/transcripts/t1",
"entries": [
{
"speaker": "John Doe",
"participant_id": "conferenceRecords/qbash-call-1/participants/p1",
"text": "Let's ship the Slides connector on Thursday.",
"language_code": "en-US",
"start_time": "2026-11-05T15:02:10Z",
"end_time": "2026-11-05T15:02:14Z"
},
{
"speaker": "Jane Roe",
"participant_id": "conferenceRecords/qbash-call-1/participants/p2",
"text": "I'll write the setup guide before then.",
"language_code": "en-US",
"start_time": "2026-11-05T15:02:15Z",
"end_time": "2026-11-05T15:02:18Z"
}
],
"text": "John Doe: Let's ship the Slides connector on Thursday.\nJane Roe: I'll write the setup guide before then.",
"next_page_token": null
}
Custom MCP server
Build a custom MCP server with Google Meet
Create a hosted MCP server that combines Google Meet tools with your other connectors, Tasks and memory folders. You choose each tool it exposes, so a server can share Google Meet reads with write tools left off.
Share the server with your team, and each person adds it to the client they already use.
Google Meet MCP questions
Can it read meeting transcripts?
Yes, when transcription was turned on during the call. get_transcript_text returns each line with the speaker’s name and time. Transcription needs a Google Workspace plan that includes it, so calls on personal Gmail accounts have none.
Which calls can it see?
Calls the connected account organized. Google keeps each call record for 30 days after the call ends, and the transcript, recording and Gemini notes files stay in the organizer’s Drive after that.
Can it change any meeting room?
It can read any room by its meeting code or link. Settings, members and ending a call work only on rooms made with create_meeting, because Google limits the Meet API to rooms the app created.
Related productivity connectors
Build a Google Meet task
Write it in Python with AI steps, or describe it to your coding agent through the qbash MCP.