Google Meet

HTTPv1.0.0Credential RequiredMay 15, 2026

Documentation

Guide

Create, manage, and inspect Google Meet sessions — directly from your AI workflows.

A Model Context Protocol (MCP) server that exposes Google Meet's API for creating meeting spaces, managing conference records, and retrieving participant information.

Overview

The Google Meet MCP Server provides full programmatic access to Google Meet through a stateless, multi-tenant interface:

Create, update, and end Google Meet meeting spaces
Retrieve conference records and meeting history
List and inspect participants and their session details

Perfect for:

Automating meeting creation and management from AI agents
Building assistants that can schedule, start, and end Meet sessions
Analyzing meeting attendance and participant data in LLM-powered pipelines

Tools

Creates a new Google Meet meeting space and returns its details including the join link.

Inputs:

none

output:

{
  "name": "spaces/abc-defg-hij",
  "meetingUri": "https://meet.google.com/abc-defg-hij",
  "meetingCode": "abc-defg-hij"
}

Fetches the current details of an existing meeting space by its resource name.

Inputs:

- `name` (string, required) — Space resource name e.g. `spaces/abc-defg-hij`

output:

{
  "name": "spaces/abc-defg-hij",
  "meetingUri": "https://meet.google.com/abc-defg-hij",
  "meetingCode": "abc-defg-hij",
  "config": { "accessType": "OPEN" }

Patches one or more fields of an existing meeting space using a field mask.

Inputs:

- `name` (string, required) — Space resource name e.g. `spaces/abc-defg-hij`
- `update_mask` (string, required) — Comma-separated field mask for the patch operation e.g. `config.accessType`
- `space` (string, required) — JSON string containing the updated space fields e.g. `{"config": {"accessType": "TRUSTED"}}`

output:

{
  "name": "spaces/abc-defg-hij",
  "meetingUri"

Retrieves a single conference record by its resource name.

Inputs:

- `name` (string, required) — Conference record resource name e.g. `conferenceRecords/abc123`

output:

{
  "name": "conferenceRecords/abc123",
  "startTime": "2024-03-20T10:00:00.000Z",
  "endTime": "2024-03-20T11:00:00.000Z",
  "space": "spaces/abc-defg-hij"

Returns a paginated list of past conference records for the authenticated user.

Inputs:

- `page_size` (integer, optional) — Maximum number of records per page
- `page_token` (string, optional) — Pagination token from a previous response

output:

{
  "conferenceRecords": [
    {
      "name": "conferenceRecords/abc123",
      "startTime": "2024-03-20T10:00:00.000Z",
      "endTime": "2024-03-20T11:00:00.000Z"

Retrieves details of a single participant from a conference record.

Inputs:

- `name` (string, required) — Participant resource name e.g. `conferenceRecords/abc123/participants/xyz`

output:

{
  "name": "conferenceRecords/abc123/participants/xyz",
  "signedinUser": {
    "user": "users/123",
    "displayName": "Jane Doe"
  },
  "earliestStartTime"

Returns a paginated list of participants for a given conference record.

Inputs:

- `parent` (string, required) — Parent conference record resource name e.g. `conferenceRecords/abc123`
- `page_size` (integer, optional) — Maximum number of participants per page
- `page_token` (string, optional) — Pagination token from a previous response
- `filter` (string, optional) — API filter expression e.g. `signedinUser.user='users/123'`

output:

{
  "participants": [
    {
      "name"

Retrieves a single participant session, representing one continuous join/leave interval.

Inputs:

- `name` (string, required) — Participant session resource name e.g. `conferenceRecords/abc123/participants/xyz/participantSessions/session1`

output:

{
  "name": "conferenceRecords/abc123/participants/xyz/participantSessions/session1",
  "startTime": "2024-03-20T10:02:00.000Z",
  "endTime": "2024-03-20T10:30:00.000Z"

Returns a paginated list of all sessions for a given participant in a conference record.

Inputs:

- `parent` (string, required) — Parent participant resource name e.g. `conferenceRecords/abc123/participants/xyz`
- `page_size` (integer, optional) — Maximum number of sessions per page
- `page_token` (string, optional) — Pagination token from a previous response
- `filter` (string, optional) — API filter expression

output:

{
  "participantSessions": [
    {
      "name": "conferenceRecords/abc123/participants/xyz/participantSessions/session1"

API Parameters Reference

name — Full resource name identifying a Meet object. Always returned in API responses and used as the identifier for subsequent calls.
page_size — Limits the number of items returned per page. If omitted, the API uses its default page size.
page_token — Token from a previous paginated response. Pass it to retrieve the next page of results.
filter — Standard API filter expression for narrowing list results.

Troubleshooting

Resources

Google Meet API Documentation — Official API reference
Google Meet API Reference — Complete endpoint reference
FastMCP Docs — FastMCP specification
FastMCP Credentials — FastMCP Credentials package for credential handling

Connect

Get connection URL

https://gateway.mewcp.com/google-meet/mcp

Code Snippets

{
  "inputs": [
    {
      "type": "promptString",
      "id": "google-meet-api-key",
      "password": true
    }
  ],
  "servers": {
    "google-meet": {
      "type": "http",
      "url": "https://gateway.mewcp.com/google-meet/mcp",
      "headers": {
        "Authorization": "Bearer ${input:google-meet-api-key}",
        "x-mewcp-credential-id": "YOUR_CREDENTIAL_ID"
      }
    }
  }
}

Request Builder

import asyncio
from fastmcp import Client

GATEWAY_URL = "https://gateway.mewcp.com/google-meet/mcp"
API_KEY = "YOUR_API_KEY"
CREDENTIAL_ID = "YOUR_CREDENTIAL_ID"

headers={
    "Authorization": f"Bearer {API_KEY}",
    "x-mewcp-credential-id": CREDENTIAL_ID,
}

async def main():
    
    client = Client(GATEWAY_URL, headers=headers)
    
    async with client:
        # Test the connection by pinging the server
        await client.ping()
        
        # List available operations
        tools = await client.list_tools()
        resources = await client.list_resources()
        prompts = await client.list_prompts()

        # Execute operations
        result = await client.call_tool("example_tool", {"param": "value"})
        print(result)

asyncio.run(main())