Google Meet

Live

OAUTH 2.0

VIDEO CONFERENCING

Every meeting room, conference link, and participant record your team manages lives in Google Meet. Google Meet MCP gives your agent authenticated access to meetings scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Google Meet account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Google Meet
agent · Acme Q3
Run
Create a Meet link for a team sync and list who attended our last all-hands recording.
S
gmeet_space_create
68ms
Meeting agent
Meet link created: meet.google.com/abc-defg-hij. Last all-hands (Oct 28): 34 participants attended. Recording available. Duration: 58 minutes.
Sources: 1 meeting space created
googlemeetmcp
1 space
18:29
Message Claude...

Tools your meeting agent reaches for on Google Meet, scoped per user.

CALL ANY TOOL
Create Meet spaces, list conference records, retrieve participants, and access recording metadata.
gmeet_space_create
Create meeting space
Create a new Google Meet conference room and return the meeting URI.
Parameters
Name
Type
Required
Description
config
object
Optional
Meeting config: accessType (open/trusted/restricted), entryPointAccess
gmeet_space_get
Get meeting space
gmeet_conference_records_list
List conference records
gmeet_participants_list
List participants
gmeet_recording_list
List recordings
Build your Agent
Drop the toolkit in, point it at the user, and your meeting agent can use Google Meet from the first run.
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googlemeet"], toolNames: ["gmeet_space_create", "gmeet_space_get", "gmeet_conference_records_list"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googlemeet"], toolNames: ["gmeet_space_create", "gmeet_space_get", "gmeet_conference_records_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googlemeet"], toolNames: ["gmeet_space_create", "gmeet_space_get", "gmeet_conference_records_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/googlemeet",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Google Meet.
Create & share
Copy the prompt
Copied
Create a Meet link for [meeting name].
Copy the prompt
Copied
Generate a restricted-access Meet for [account name].
Copy the prompt
Copied
Create a Meet with trusted access for the [team] sync.
Copy the prompt
Copied
Get the meeting URI for [meeting code].
Records & attendance
Copy the prompt
Copied
List past conference records this week.
Copy the prompt
Copied
Who attended the [meeting name] on [date]?
Copy the prompt
Copied
List all recordings from this month.
Copy the prompt
Copied
How many participants joined [meeting name]?
Reporting
Copy the prompt
Copied
Which meetings had fewer attendees than expected?
Copy the prompt
Copied
List all recordings longer than 60 minutes.
Copy the prompt
Copied
Find all Meet sessions on [date].
Copy the prompt
Copied
List meetings with no recording.
SEE HOW AUTH WORKS
Users authorize Google Meet once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Google Meet
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Google Meet
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Google Meet
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Google Meet
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other meeting agents and MCP connectors. Working code, live demos, fork what fits.
OPS
Email-to-calendar scheduling agent
Parse scheduling intent from Gmail threads and create Google Calendar events with the right attendees and timezone.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Google Meet today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions

Does the agent access Google Meet as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Google Meet oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Google Meet?
Yes. Pass a tool name filter to listScopedTools so the meeting agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Google Meet.

What happens when a user revokes Google Meet access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent join or record a live meeting on the user's behalf?
No. The agent creates and retrieves meeting links but cannot join a live call or trigger recording. Recording is governed by the meeting host's Workspace admin policy.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""googlemeet"": {
""url"": ""https://mcp.scalekit.com/googlemeet"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.googlemeet]
url = ""https://mcp.scalekit.com/googlemeet""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""googlemeet"": {
""url"": ""https://mcp.scalekit.com/googlemeet"",
""type"": ""http""
}
}
}