Google Chat connector for AI agents

Tools your team chat agent reaches for on Google Chat, scoped per user.

CALL ANY TOOL

54 tools for team chat in Google Chat: list and search messages, send and edit messages, and manage spaces, members, reactions, pins, sections, read state, and availability.

googlechat_complete_space_import

Import complete space

Complete the import process for a space that was created in Import Mode, making it visible to users. Call this after all historical messages and memberships have been migrated into the space; if you miss the space's importModeExpireTime, Google Chat automatically deletes the space. Returns a CompleteImportSpaceResponse containing the finalized space. Requires a valid Google Chat OAuth2 connection with the chat.import scope and domain-wide delegation. Known limitation: this endpoint has no fallback scope -- it strictly requires chat.import, which is not currently offered in the standard Google Cloud Console OAuth consent screen scope picker (observed directly; likely a Developer-Preview-gated scope on Google's side). Calls will fail with an insufficient-scope/permission error until Google exposes it for this project.

Parameters

Name

Type

Required

Description

space_id

string

Required

The unique ID of the import-mode space to finalize (the segment after 'spaces/' in the space resource name)

googlechat_create_custom_emoji

Create custom emoji

googlechat_create_member

Create member

googlechat_create_message_pin

Create message pin

googlechat_create_section

Create section

googlechat_delete_custom_emoji

Delete custom emoji

googlechat_delete_member

Delete member

googlechat_delete_message_pin

Delete message pin

googlechat_delete_section

Delete section

googlechat_find_direct_message_space

Find direct message space

googlechat_get_attachment

Get attachment

googlechat_get_custom_emoji

Get custom emoji

googlechat_get_message

Get message

googlechat_get_space_event

Get space event

googlechat_get_space_notification_setting

Get space notification setting

googlechat_get_thread_read_state

Get thread read state

googlechat_list_custom_emojis

List custom emojis

googlechat_list_members

List members

googlechat_list_messages

List messages

googlechat_list_section_items

List section items

googlechat_list_space_events

List space events

googlechat_mark_user_active

Mark user active

googlechat_mark_user_do_not_disturb

Mark user do not disturb

googlechat_replace_message

Replace message

googlechat_search_messages

Search messages

Search Google Chat messages the caller has access to across all spaces, using a structured filter query. Returns matching message resources, each with the space they belong to, plus a page token for further results. Google's API only supports searching across all spaces at once (there is no per-space search endpoint) -- scope results to one space with `filter`, e.g. 'space.name = "spaces/AAAAAAAAAAA"'. Use search_messages for text and field-based queries. Use list_messages to page through every message in one already-known space. Requires a valid Google Chat OAuth2 connection.

Parameters

Name

Type

Required

Description

filter

string

Required

Required. A search query. Supports keyword search plus field filters such as create_time (RFC-3339 timestamp, with < or >=), sender.name (users/{user} or an email), space.name, space.display_name (partial match with ':'), and attachment. Combine conditions with AND.

markup_syntax

string

Optional

Output syntax for the formatted_text field on returned messages. One of: `MARKUP_SYNTAX_UNSPECIFIED`, `MARKUP_SYNTAX_CHAT`, `MARKUP_SYNTAX_MARKDOWN`.

order_by

string

Optional

How the results are ordered. create_time (default) sorts by message creation time, descending. relevance also sorts descending, but is a Google Workspace Developer Preview feature -- confirmed via live testing that projects not enrolled in that program get rejected with 'The Google Cloud project isn't allowed to call this API. To call this API, join the Google Workspace Developer Preview program.' Use create_time desc unless you know your project is enrolled. One of: `create_time desc`, `relevance desc`.

page_size

integer

Optional

Maximum number of results to return. If unspecified, at most 25 are returned. The maximum value is 100; larger values are automatically capped.

page_token

string

Optional

A page token from a previous search_messages call, used to retrieve the next page of results. Other parameters should match the original call.

view

string

Optional

How much detail to return per matched message. BASIC returns only the matched messages; FULL includes additional metadata. One of: `SEARCH_MESSAGES_VIEW_UNSPECIFIED`, `SEARCH_MESSAGES_VIEW_BASIC`, `SEARCH_MESSAGES_VIEW_FULL`.

googlechat_update_member

Update member

googlechat_update_section

Update section

googlechat_update_space_notification_setting

Update space notification setting

googlechat_update_space_read_state

Update space read state

googlechat_upload_media

Upload media

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Google Chat tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlechat"], toolNames: [
    "googlechat_list_spaces",
    "googlechat_search_messages",
    "googlechat_create_message"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find messages about the Q3 launch from this week" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlechat"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find messages about the Q3 launch from this week" }],
  tools,
});

// Execute the tool call with the user's vaulted Google Chat token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlechat"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find messages about the Q3 launch from this week" }],
  tools,
});

// Tool call runs with the user's vaulted Google Chat token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googlechat"] }, pageSize: 100,
});

const agent = new Agent({
  name: "team_chat_agent",
  model: "gemini-2.5-pro",
  instruction: "Google Chat tools scoped to this user",
  tools,
});

await agent.run("Find messages about the Q3 launch from this week");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Google Chat tool. Click to copy, paste into your agent, done.

Messages

Copy the prompt

Copied

Search my spaces for messages about the Q3 launch from this week.

Copy the prompt

Copied

Post a rollout status update in the Product space.

Copy the prompt

Copied

Pin the latest release notes message in the Engineering space.

Spaces and members

Copy the prompt

Copied

List the spaces I belong to.

Copy the prompt

Copied

Create a space called Launch Room and add these three teammates.

Copy the prompt

Copied

Promote this member to space manager.

Availability and organization

Copy the prompt

Copied

Set me to do not disturb for the next two hours.

Copy the prompt

Copied

Mute notifications for the Random space.

Copy the prompt

Copied

Move the Launch Room space into my Projects section.

SEE HOW AUTH WORKS

Each user signs in to Google Chat once; Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Google Chat

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

Store

Their

Google Chat

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

Resolve

When your agent calls a

Google Chat

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

Audit

Every

Google Chat

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

See the same per-user auth pattern across other communication connectors.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Google Chat token looks fine in a demo. In production every message the agent posts looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Google Chat today. Ten connectors 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 Chat as the user or through a shared service account?

As the user. Each user signs in to Google Chat once, and Scalekit stores and refreshes their tokens. Messages the agent sends and reads are attributed to that user in your audit trail, not a shared service account.

Where is the Google Chat OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Google Chat?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read and search tools without googlechat_delete_space. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Google Chat 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 search spaces across the whole organization?

Only with admin access. googlechat_search_messages searches messages the signed-in user can see across all their spaces. googlechat_search_spaces searches spaces across a Google Workspace organization and requires domain-wide admin access with a Chat admin scope.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit