Official vendor OpenAPI document · agent-readyCommunicationsChat Messagingoauth219 EndpointsREST
For Agents
Create Google Chat spaces, post and update messages with rich cards, manage memberships, and operate Chat bots and apps inside Google Workspace.
Use for: Post a message to a Google Chat space, Send a card with action buttons to a Chat space, Find the direct message space between two users, List all spaces a Chat app is a member of
Not supported: Does not handle email, video meetings, or SMS - use for Google Chat space, message, and membership operations only.
The Google Chat API lets applications and bots create and manage spaces, post and update messages, react to user actions, and integrate Chat into automation workflows alongside the rest of Google Workspace. It supports both bot accounts (Chat apps) and user-impersonating OAuth flows, exposing membership management, attachments, message threading, and rich card-based messages. Common uses include incident response bots, deploy notifications, on-call paging, and AI assistants embedded in team conversations.
Install Jentic One Beta
Connect the Google Chat API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Google Chat API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fchat" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fgoogleapis.com%2Fchat" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Google Chat API.
Create direct messages and named spaces between users and Chat apps
Post text and card-formatted messages to a space, optionally inside a thread
Update or delete messages previously posted by the calling Chat app
Manage memberships by adding, removing, and listing space members
Upload and download attachments tied to a Chat message
Search for spaces and find the direct-message space between two users
Use Cases
Patterns agents use Google Chat API for, with concrete tasks.
★ Incident Response Notifications
DevOps teams wire monitoring tools into a Google Chat app that creates an incident space, posts a structured card with severity and runbook links, and adds the on-call responders as members. The same app can post status updates to the original thread as the incident progresses. Card messages render the same on web and mobile.
Create a space named "INC-1234 - payments-api 5xx spike", add on-call@example.com as a member, and post a card message with severity SEV2 and a runbook link.
Deploy and CI Notifications
Engineering teams post deploy and CI status messages to a #releases space from their pipeline. The Chat app uses a single POST /v1/spaces/{space}/messages call per event and threads follow-up messages under the original deploy message. This replaces email blasts with a single readable timeline per release.
Post a threaded message under deploy parent thread with text "deploy to prod completed: build #482" via /v1/spaces/{space}/messages with messageReplyOption=REPLY_MESSAGE_FALLBACK_TO_NEW_THREAD.
AI Assistant Embedded in a Team Space
An AI assistant joins a project space as a Chat app, listens for slash commands or @mentions, and responds with summaries, action items, or links to ticket creation. The assistant uses spaces.messages to reply and spaces.members to enumerate participants for context. Workspace admin approval is required for the Chat app to publish to other domains.
When a slash command /summarise is received, post a reply in the same thread with a summary of the last 50 messages in the space.
AI Agent Workspace Operator via Jentic
An AI agent through Jentic acts as a project assistant - creating a Chat space for a new initiative, inviting the right teammates by email, posting an onboarding card, and uploading the kickoff doc as an attachment. Jentic isolates the Workspace OAuth credentials and exposes the Chat operations as named tools.
Through Jentic, search chat_create_message, load schema, and execute it for space spaces/AAAA with text "Kickoff at 10am - agenda attached".
Key Endpoints
19 endpoints — the google chat api lets applications and bots create and manage spaces, post and update messages, react to user actions, and integrate chat into automation workflows alongside the rest of google workspace.
METHOD
PATH
DESCRIPTION
POST
/v1/spaces
Create a Chat space
GET
/v1/spaces
List spaces a Chat app is a member of
GET
/v1/spaces:findDirectMessage
Find the direct message space between two users
POST
/v1/spaces:setup
Create a space and add members in a single call
PUT
/v1/{+name}
Update a previously posted message
POST
/v1/{+parent}/attachments:upload
Upload an attachment for a Chat message
POST
/v1/spaces
Create a Chat space
GET
/v1/spaces
List spaces a Chat app is a member of
GET
/v1/spaces:findDirectMessage
Find the direct message space between two users
POST
/v1/spaces:setup
Create a space and add members in a single call
PUT
/v1/{+name}
Update a previously posted message
POST
/v1/{+parent}/attachments:upload
Upload an attachment for a Chat message
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
G
Google Chat API
- Foundational (D-)42/100
47
Foundational Compliance56
Developer Experience & Jentic Compatibility21
AI-Readiness & Agent Experience91
Agent Usability63
Security62
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
47
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: D+Signals: 4
53%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
35%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
56
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: CSignals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
25%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
21
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
85%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
0%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
0%
Summary Coverage
Coverage of summaries across operations/tags/info.
91
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
91%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
63
Security
Trust, risk posture, and security compliance.
Grade: B-Signals: 1
62%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
62
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B-Signals: 1
62%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Google Chat API by hand means standing up Workspace OAuth or a Chat app service account, refreshing scoped access tokens, and assembling space, message, and membership calls with cardsV2 layouts yourself. Through Jentic you install once, import the Google Chat API from the API Directory, store the credential once, and your agent calls it.
Permission scoping
Chat puts the space and resource in the URL path for name-based operations (/v1/{+name}, /v1/{+parent}/attachments:upload), so a rule can pin your agent to the spaces it works in and limit it to the operations it needs, such as creating a space or posting a message. You choose those operations, so ones like deleting a space are not included unless you add them.
Credential isolation
Your Workspace OAuth credentials or Chat app service account are stored once, encrypted, by your own Jentic One instance and injected at execution time. The agent receives only short-lived access tokens and the refresh token and service account JSON never enter its prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'post a Google Chat message' or 'set up a new space', and Jentic returns the matching spaces operation with its parameter schema, including cardsV2 layout support, so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Google Chat API through Jentic.
What authentication does the Google Chat API use?
It supports two flows: a Chat app service account using OAuth 2.0 with the chat.bot scope, and user-impersonation OAuth with scopes such as chat.spaces and chat.messages. Through Jentic, the chosen credential is stored encrypted in your Jentic One instance and the agent receives only short-lived access tokens.
Can I post a message to a Google Chat space via the API?
Yes. POST to /v1/{parent}/messages where parent is the space resource name (spaces/AAAA). The body can include text, cardsV2 for rich card layouts, and threadKey or thread.name to post inside an existing thread.
What are the rate limits for the Google Chat API?
Google Workspace applies per-app per-user write quotas, typically around 60 messages per minute per space for a single Chat app, with higher project-level quotas. Bursts above the per-space rate return 429 and require backoff.
How do I create a Chat space through Jentic?
Use the Jentic search query "create a Google Chat space" to discover the spaces.create operation, load its schema, and execute it with displayName and spaceType (SPACE or DIRECT_MESSAGE). Run pip install jentic to get started.
Can a Chat app update or delete messages?
A Chat app can update and delete only the messages it posted itself. Use PUT /v1/{+name} with an updateMask covering the fields to change, and DELETE /v1/{+name} to remove a message.
Is the Google Chat API free?
The API itself has no per-call charge. It is available to Google Workspace customers; some features (such as enterprise external Chat apps) require specific Workspace editions.
Can I limit what my agent is allowed to do with the Google Chat API?
Yes. Because Jentic One is self-hosted, your own rules decide which Google Chat operations and credentials the agent may use. Google Chat carries the space and resource in the URL path for name-based operations like /v1/{+name} and /v1/{+parent}/attachments:upload, so you can pin the agent to the specific spaces it works in and grant only the operations it needs, such as creating a space or posting a message. Higher-impact calls like deleting a space are excluded unless you explicitly add them.
GET STARTED