Integration
Connect Cursor to Chatwork
When Agent Pull Request Created fires in Cursor, your agent runs Create Task in Chatwork. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Cursor and Chatwork to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What Cursor can start in Chatwork
When Agent Pull Request Created in Cursor
then Create Task in Chatwork
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Cursor and Chatwork
Triggers and actions 3 triggers · 28 actions
- Agent Pull Request Created
Triggers when the selected Cursor cloud agent opens a new GitHub pull request.
- Agent Status Equals
Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error.
- New Agent
Triggered when a new Cursor cloud agent is created.
- Add Followup Instruction to Agent
Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered.
- Cancel run
Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation.
- Delete Agent
Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent.
- Find Agent Status
Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link.
- Get run
Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent.
- Launch Agent
Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run.
- List agents
Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL.
- List artifacts
Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts.
- List models
Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants.
- List repositories
Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation.
- List runs
Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply.
- Add file
Uploads a file to a Chatwork chat room, optionally with a message posted alongside it, and returns the new file's ID.
- Create Task
Adds a task to a Chatwork chat and assigns it to one or more chat members, with an optional due date.
- Delete message
Deletes a message you posted in a Chatwork chat room.
- Get me
Returns the profile of the Chatwork account that is connected, including its account ID, name, organization, contact details and the ID of its personal chat.
- Get message
Returns a single message from a Chatwork chat room, including its text, sender and send/update times.
- Get room
Returns a chat room's details: its name, type, your role, description, icon, and message, file and task counts.
- Get task
Returns one task in a Chatwork chat room: its assignee, requester, content, due date and whether it is open or done.
- List contacts
Returns every contact of the connected Chatwork user, including each contact's account ID, direct-chat room ID, name, organization and department.
- List files
Returns the files uploaded to a Chatwork chat room (up to 100), optionally only those uploaded by one member.
- List messages
Returns up to the 100 most recent messages in a Chatwork chat room, by default only those new since the last listing.
- List room members
Returns every member of a Chatwork chat room, with each member's role, name, Chatwork ID, organization and department.
- List rooms
Returns every Chatwork chat (my chat, direct chats and group chats) the connected account belongs to, with unread, mention, task and file counts.
- List tasks
Returns the tasks in a Chatwork chat room (up to 100), optionally filtered by assignee, requester or status.
- Send Message
Posts a new message to a Chatwork chat.
- Update message
Edits the text of a message you posted in a Chatwork chat room.
- Update room
Changes a group chat's name, description or icon. Fields left blank keep their current values.
- Update task
Marks a task in a Chatwork chat as done or reopens it as not done.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Cursor
Cursor to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursor to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursor to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursor to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Cursor to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursor to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Chatwork
Questions
Cursor and Chatwork, answered
What can start an automation from Cursor?
Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Chatwork when something happens in Cursor?
Any of Chatwork's 17 actions, including Create Task, Send Message, Update message and Update room. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Chatwork to Cursor?
Chatwork has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads Chatwork's API documentation and adds it.
Do I have to build a connector for Cursor or Chatwork?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Cursor and Chatwork without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.