Chatwork for AI agents
Chatwork is a business chat platform combining group messaging, file sharing, and task tracking, aimed at teams that want collaboration without separate tools. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Chatwork.
Post a message to a room
Post a message into a Chatwork room to update the team on progress.
Create a task in a room
Create a task inside a room and assign it to a specific member.
Confirm before deleting a message
Confirm before deleting a posted message, since it disappears from the room for everyone.
30 Chatwork actions, graded by risk.
Every Chatwork action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
15Look things up. Allowed by default.
- chatwork.get_meGet My Chatwork Profile
- chatwork.get_roomGet Chatwork Room
- chatwork.get_taskGet Task
- chatwork.get_file2Get Chatwork File Information
- chatwork.get_rooms2Get Chatwork Rooms
- chatwork.get_messageGet Message
- chatwork.get_my_tasksGet My Chatwork Tasks
- chatwork.get_my_statusGet My Chatwork Status
- chatwork.get_room_linkGet Room Invitation Link
- chatwork.get_room_filesGet Room Files
- chatwork.get_room_tasksGet Room Tasks
- chatwork.get_room_membersGet Room Members
- chatwork.get_room_messages2Get Room Messages V2
- chatwork.get_chatwork_contactsGet Chatwork Contacts
- chatwork.get_incoming_requestsGet Incoming Contact Requests
write
12Create and change things. Allow, or ask the user first.
- chatwork.create_roomCreate Chatwork Room
- chatwork.create_taskCreate Task in Chatwork Room
- chatwork.update_roomUpdate Chatwork Room
- chatwork.post_messagePost Message
- chatwork.update_messageUpdate Message
- chatwork.create_room_linkCreate Room Invitation Link
- chatwork.update_room_linkUpdate Room Invitation Link
- chatwork.update_task_statusUpdate Task Status
- chatwork.update_room_membersUpdate Room Members
- chatwork.upload_fileUpload File to Chatwork Room
- chatwork.mark_messages_readMark Messages as Read
- chatwork.mark_messages_unreadMark Messages as Unread
destructive
3Delete, cancel or archive. Ask first, or deny outright.
- chatwork.delete_roomDelete or Leave Chatwork Room
- chatwork.delete_messageDelete Message
- chatwork.delete_room_linkDelete Room Link
Chatwork in three steps.
- 01Your users connect ChatworkThey add their Chatwork api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Chatwork Room” can wait for the user, and “delete or Leave Chatwork Room” can be denied outright.
- 03Any agent can actYour agent calls Chatwork through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('chatwork', { read: 'allow', write: 'ask', // create_room destructive: 'deny', // delete_room }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Chatwork connects.
Users add their Chatwork api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Chatwork connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Chatwork from any agent.
Chatwork and Arc0, answered.
Can I use Chatwork with Claude, ChatGPT or Cursor?
Yes. Connect Chatwork to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Chatwork actions you allow.
How do users connect Chatwork?
Users add their Chatwork api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Chatwork actions can my agent take?
30 in total: 15 read, 12 write and 3 destructive, such as “create Chatwork Room”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Chatwork?
Yes. Actions like “delete or Leave Chatwork Room” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Chatwork too?
Yes. The same Chatwork connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Chatwork into your agent.
Your users connect Chatwork once, under your brand. Your agent gets 30 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan