How to Connect Chatwork MCP to an AI Agent
Auth setup
Easiest: Go to chatwork.com > Settings > API Token > generate. Use X-ChatWorkToken header. No app registration needed for personal token.
Key facts
| Base URL | https://api.chatwork.com/v2/ |
| API version | v2 |
| Auth | API token (simplest) or OAuth 2.0. API token: generate at chatwork.com/service/packages/chatwork/subpackages/api/token. Include as X-ChatWorkToken header. OAuth: register app at developer.chatwork.com. |
| Token URL | https://oauth.chatwork.com/token |
| Scopes | rooms.all:read_write,contacts.all:read |
| Request body | application/x-www-form-urlencoded |
| Pagination | No standard pagination. Messages: use force=1 to get latest 100. Tasks: returned as full list. |
| Rate limit | 300 requests/5 minutes. HTTP 429 response. Check X-RateLimit-Remaining header. |
| Error format | JSON: {"errors":["message string"]} |
Key endpoints
| Method | Path | Description |
GET | /me | Get your own account info |
GET | /rooms | List chat rooms you belong to |
POST | /rooms/{room_id}/messages | Send a message to a room |
GET | /rooms/{room_id}/messages | Get messages from a room |
POST | /rooms/{room_id}/tasks | Create a task in a room |
Quickstart
POST /v2/rooms/123456/messages HTTP/1.1
Host: api.chatwork.com
X-ChatWorkToken: {your_token}
Content-Type: application/x-www-form-urlencoded
body=Hello+from+agent!
Response: {"message_id":"789"}
Agent pitfalls & tips
- POST body uses application/x-www-form-urlencoded, NOT JSON. This is unusual — most agents default to JSON and get 400 errors.
- Message body supports [info][title]Title[/title]Content[/info] tags for formatted messages. Use [To:account_id] for mentions.
- Room IDs are numeric. Get them from GET /rooms first.
- Task deadlines use Unix timestamps (seconds, not milliseconds).
- Rate limit is strict (300/5min) — batch operations carefully.
Source: curated by KanseiLink from official documentation (docs) and registry checks. Last reviewed: 2026-04-04. Specs change — verify against the official docs before production use.
Frequently Asked Questions
What is Chatwork MCP's AEO score?
▼
Chatwork MCP has an AEO score of 0.90 and is rated AA (Strong agent support with minor gaps). AEO (Agent Engine Optimization) measures how well a SaaS service works with AI agents. Scores range from 0.00 to 1.00, with grades from AAA (best) to D (not agent-ready).
Is Chatwork MCP AI-agent-ready?
▼
Chatwork MCP is currently ✓ verified for AI agent use. It offers an official MCP (Model Context Protocol) server, which means AI agents can connect directly. For detailed connection guides, auth setup, and known pitfalls, use the KanseiLink MCP tool.
How does Chatwork MCP compare to other Communication services?
▼
In the Communication category, Chatwork MCP is rated AA. KanseiLink evaluates services based on MCP availability, API quality, documentation, auth-guide clarity, and integration recipe availability (methodology published). Visit the full rankings at kansei-link.com to see how Chatwork MCP compares.
How can I integrate Chatwork MCP with an AI agent?
▼
The fastest way to integrate Chatwork MCP with an AI agent is through KanseiLink MCP. Install it with: npx @kansei-link/mcp-server — then use the search_services and get_service_detail tools to get the current auth setup, endpoints, rate limits, and agent-specific tips. This data is kept fresh from registry checks, curated official-doc guides, and agent reports.
How do I authenticate with Chatwork MCP?
▼
API token (simplest) or OAuth 2.0. API token: generate at chatwork.com/service/packages/chatwork/subpackages/api/token. Include as X-ChatWorkToken header. OAuth: register app at developer.chatwork.com. Setup: Easiest: Go to chatwork.com > Settings > API Token > generate. Use X-ChatWorkToken header. No app registration needed for personal token.
What are Chatwork MCP's API rate limits?
▼
300 requests/5 minutes. HTTP 429 response. Check X-RateLimit-Remaining header.