Agent-ready OpenAPI document · curated by JenticCommunicationsChat MessagingapiKey32 EndpointsREST
Know of an official OpenAPI document? Contribute it →
For Agents
Post messages, create tasks, manage rooms, and upload files in Chatwork so an agent can run team chat workflows end to end.
Use for: Post a message to a Chatwork room, Create a task in a room and assign it to a teammate, List all of my unread Chatwork rooms, Find tasks assigned to me that are due today
Not supported: The 32 operations in this spec cover group chat rooms, messages, tasks, files, contacts, and invitation links only - there are no endpoints for voice calls, video conferencing, or an external customer support inbox.
Chatwork is a cloud-based business chat tool for team messaging, task management, and file sharing inside group chat rooms. The v2 REST API exposes 32 endpoints covering rooms, messages, tasks, files, contacts, and invitation links - enough to fully automate room creation, message posting, task tracking, and file uploads. It is well suited to teams building bots, integrations, or migration tools on top of Chatwork.
Install Jentic One Beta
Connect the Chatwork API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Chatwork 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%2Fchatwork.com%2Fchatwork" | 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%2Fchatwork.com%2Fchatwork" | 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 Chatwork API.
Post and update messages in any Chatwork group chat room
Create and complete tasks tied to specific rooms and assignees
Provision new group chat rooms with members and roles
Upload files to rooms and fetch file metadata
Mark messages read or unread on behalf of a user
Manage room invitation links for inviting new members
Read your own contacts, tasks, and unread counts via the /me endpoints
Use Cases
Patterns agents use Chatwork API for, with concrete tasks.
★ Project Room Bot
Run a bot that posts daily standup prompts, creates tasks from meeting notes, and uploads weekly reports into a project's Chatwork room. The bot uses POST /rooms/{room_id}/messages to send updates, POST /rooms/{room_id}/tasks to file action items, and POST /rooms/{room_id}/files to share artefacts - turning Chatwork into the project's operational hub.
Post 'Daily standup at 10:00' to room_id 12345 and create three tasks for users 100, 101, 102 due tomorrow.
Task Automation
Mirror tasks between Chatwork and an external project tracker. Pull /my/tasks for the current user, sync new items into the tracker, and create matching tasks in Chatwork with POST /rooms/{room_id}/tasks when issues are filed elsewhere. Useful for teams that live in Chatwork but report into Jira or Linear.
Fetch /my/tasks and return the count of incomplete tasks due in the next 7 days.
Onboarding and Room Provisioning
When a new project starts or a new hire joins, automatically create a Chatwork room, invite the right members, and post a welcome message with onboarding links. POST /rooms creates the room, PUT /rooms/{room_id}/members updates membership, and POST /rooms/{room_id}/link generates a shareable invite for guests.
Create a room called 'Project Atlas Kickoff' with members [100, 101, 102] as admin and post a welcome message.
AI Agent for Chatwork Workflows
An autonomous agent reads unread Chatwork rooms, drafts replies based on prior context, files action items as tasks, and posts them - all through Jentic without holding the X-ChatWorkToken in agent memory. Jentic's intent search lets the agent pick the right Chatwork operation with one query.
Through Jentic, search 'post a message to a chatwork room', load the schema, and execute with room_id 12345 and body 'Acknowledged'.
Key Endpoints
32 endpoints — chatwork is a cloud-based business chat tool for team messaging, task management, and file sharing inside group chat rooms.
METHOD
PATH
DESCRIPTION
POST
/rooms/{room_id}/messages
Post a message to a room
GET
/rooms/{room_id}/messages
Get messages in a room
POST
/rooms/{room_id}/tasks
Create a task in a room
GET
/my/tasks
Get your task list
POST
/rooms
Create a new group chat room
POST
/rooms/{room_id}/files
Upload a file to a room
GET
/me
Get your account information
POST
/rooms/{room_id}/messages
Post a message to a room
GET
/rooms/{room_id}/messages
Get messages in a room
POST
/rooms/{room_id}/tasks
Create a task in a room
GET
/my/tasks
Get your task list
POST
/rooms
Create a new group chat room
POST
/rooms/{room_id}/files
Upload a file to a room
GET
/me
Get your account information
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.
C
Chatwork API
- AI-Aware (B+)67/100
99
Foundational Compliance63
Developer Experience & Jentic Compatibility49
AI-Readiness & Agent Experience94
Agent Usability50
Security100
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
99
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A+Signals: 4
97%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
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.
49
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: D+Signals: 4
33%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
64%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
50
Security
Trust, risk posture, and security compliance.
Grade: C-Signals: 1
50%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
100
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A+Signals: 1
100%
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 Chatwork by hand means handling its X-ChatWorkToken header and finding the right call among 32 endpoints for rooms, messages, tasks, and files. Through Jentic you install once, import the Chatwork API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Chatwork puts the room id in the URL path (/rooms/{room_id}/...), so a rule can pin your agent to one room: it can post messages, add tasks, and upload files there and nothing else. You choose the operations it may call, so creating new rooms is not included unless you add it.
Credential isolation
Your Chatwork X-ChatWorkToken is stored once, encrypted, by your own Jentic One instance and injected into the header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'post a message to a chatwork room', and Jentic returns the matching Chatwork operation with its input schema so the agent picks the right endpoint among 32 without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Chatwork API through Jentic.
Does Chatwork publish an official OpenAPI spec?
Yes. Chatwork embeds a machine-readable OpenAPI 3.1.0 definition titled 'Chatwork API', version v2, on each reference page at developer.chatwork.com, one operation per page. The document Jentic serves here is its own OpenAPI 3.0.3 spec, curated for agent use; it is not a copy of Chatwork's, and the two operation sets are close but not identical. 31 of the 32 operations here match Chatwork's definition, and the operation that changes a task's completion state is recorded at a different path there than it is here. Get started with Jentic One, the self-hosted execution layer.
Is there a Chatwork MCP server?
You don't need an MCP server to give your agent Chatwork. Jentic connects it directly from the API Directory: import the Chatwork API, store your X-ChatWorkToken once, and your agent calls it.
What authentication does the Chatwork API use?
The spec behind this page declares an API key passed in the X-ChatWorkToken header, and Chatwork generates those tokens per user from the account settings page. Chatwork's own OpenAPI definition on developer.chatwork.com additionally declares OAuth 2.0 with an authorization-code flow and per-resource scopes such as rooms.messages:write. Through Jentic, the credential is stored encrypted in your Jentic One instance and injected at execution time, so agents never see the raw value.
Can I post messages to a Chatwork room with the API?
Yes. POST /rooms/{room_id}/messages accepts a body parameter and posts the message to the specified room. Chatwork supports its own [To:] and [info] tags inside message bodies for mentions and styling.
How do I create a task in Chatwork via the API?
Use POST /rooms/{room_id}/tasks with the body, assigned account ids (to_ids), and an optional limit timestamp. The endpoint returns the created task ids, which you can later mark complete with the task status update operation.
What are the rate limits for the Chatwork API?
Chatwork's documentation states a limit of 300 API requests per 5 minutes, with the remaining call count and the reset time returned in response headers. Posting messages or tasks to a room is capped separately at 10 calls per 10 seconds. Exceeding either limit returns HTTP 429, so retry with backoff and batch reads where possible.
How do I post a message to Chatwork through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh` on the machine hosting your instance, then run `jentic register` on the separate machine where your agent runs. Add the Chatwork API from the API Directory, store your token once, and ask the agent to post the message: Jentic resolves the intent to POST /rooms/{room_id}/messages and injects the X-ChatWorkToken header at execution time.
Can I limit what my agent is allowed to do with the Chatwork API?
Yes. Because Chatwork puts the room id in the URL path (/rooms/{room_id}/...), a rule in your self-hosted Jentic One instance can pin your agent to a single room, letting it post messages, add tasks with POST /rooms/{room_id}/tasks, and upload files there and nothing else. You choose which operations the agent may call, so creating new group chat rooms with POST /rooms is excluded unless you add it. Your own rules decide which endpoints and the X-ChatWorkToken credential the agent can use at execution time.
GET STARTED