--- title: "Connect CrewForm and Cursor - APIANT.ai" description: "When \"AI Agent Task Failed\" fires in CrewForm, your agent runs \"List agents\" in Cursor." canonical: "https://apiant.ai/connect/crewform-to-cursor" --- # Connect CrewForm and Cursor When **AI Agent Task Failed** fires in [CrewForm](https://apiant.ai/connections/crewform), your agent runs **List agents** in [Cursor](https://apiant.ai/connections/cursor), or **Agent Pull Request Created** in Cursor to **Add agent** in CrewForm. Describe the whole flow and it is built, tested on every scenario and kept running. CrewForm **1** trigger CrewForm **10** actions Cursor **3** triggers Cursor **11** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want CrewForm and Cursor to do together? Give your AI client this address. `https://mcp.apiant.ai` One 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.ai` Start Claude Code there, approve the server, and sign in in the browser page it opens. [Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) Example flows ## What CrewForm and Cursor can do together ### From CrewForm to Cursor - When **AI Agent Task Failed** in CrewForm then **List agents** in Cursor - When **AI Agent Task Failed** in CrewForm then **Launch Agent** in Cursor ### From Cursor to CrewForm - When **Agent Pull Request Created** in Cursor then **Add agent** in CrewForm - When **New Agent** in Cursor then **Update agent** in CrewForm 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 CrewForm and Cursor ## Triggers and actions 4 triggers · 21 actions - Trigger **AI Agent Task Failed** Triggers when a CrewForm AI agent task fails. - Action **Add agent** Creates a new AI agent in your CrewForm workspace with the model, instructions and settings you choose. - Action **Delete agent** Deletes an AI agent from your CrewForm workspace. - Action **Delete task** Deletes a task from your CrewForm workspace. - Action **Get agent** Returns a single CrewForm agent by its id, including its model, prompt and settings. - Action **Get task** Returns a single CrewForm task by its id, including its title, status, priority, assigned agent and results. - Action **List agents** Returns all AI agents in your CrewForm workspace, with each agent's name, model, prompt and settings. - Action **List tasks** Returns the tasks in your CrewForm workspace, newest first, optionally only those with a given status. - Action **Send Task to AI Agent** Creates a task in CrewForm assigned to an AI agent, which dispatches it to that agent to work on right away. Returns the created task. - Action **Update agent** Updates an existing CrewForm agent's name, model, prompt, temperature, tools, status or configuration. Only the fields you fill in are changed. - Action **Update task** Updates an existing CrewForm task's title, description, priority, status, assigned agent or team, or metadata. - Trigger **Agent Pull Request Created** Triggers when the selected Cursor cloud agent opens a new GitHub pull request. - Trigger **Agent Status Equals** Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error. - Trigger **New Agent** Triggered when a new Cursor cloud agent is created. - Action **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. - Action **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. - Action **Delete Agent** Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent. - Action **Find Agent Status** Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link. - Action **Get run** Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent. - Action **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. - Action **List agents** Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL. - Action **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. - Action **List models** Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants. - Action **List repositories** Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation. - Action **List runs** Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply. ## Each app on its own - [ **CrewForm** CrewForm is a AI team builder. Create specialised agents — researchers, writers, coders — orchestrate them...](https://apiant.ai/connections/crewform) - [ **Cursor** Cursor is an AI-powered code editor that understands your codebase, supports natural-language coding...](https://apiant.ai/connections/cursor) Reviews ## What our customers say ## More from CrewForm - [ **CrewForm to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/crewform-to-hubspot) - [ **CrewForm to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/crewform-to-salesforce) - [ **CrewForm to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/crewform-to-slack) - [ **CrewForm to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/crewform-to-google-sheets) - [ **CrewForm to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/crewform-to-gmail) - [ **CrewForm to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/crewform-to-google-calendar) ## More into Cursor - [ **ActiveCampaign to Cursor** ActiveCampaign is a marketing automation, email marketing, and CRM platform.](https://apiant.ai/connect/activecampaign-to-cursor) - [ **Airtable to Cursor** Organize anything with Airtable, a modern database created for everyone.](https://apiant.ai/connect/airtable-to-cursor) - [ **Asana to Cursor** Asana is a collaborative information manager for workspace.](https://apiant.ai/connect/asana-to-cursor) - [ **ClickUp to Cursor** ClickUp is an all-in-one app to plan, track, and manage your work in a beautifully intuitive environment.](https://apiant.ai/connect/clickup-to-cursor) - [ **Brevo to Cursor** Brevo is the leading CRM suite designed to cultivate long-term customer relationships and help businesses...](https://apiant.ai/connect/brevo-to-cursor) - [ **Calendly to Cursor** Calendly is a scheduling automation platform for eliminating the back-and-forth emails to find the perfect...](https://apiant.ai/connect/calendly-to-cursor) Questions ## CrewForm and Cursor, answered ### ### What can start an automation from CrewForm? Any of CrewForm's 1 trigger in the catalog, including AI Agent Task Failed. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Cursor when something happens in CrewForm? Any of Cursor's 11 actions, including Add Followup Instruction to Agent, Find Agent Status, Get run and Launch Agent. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Cursor to CrewForm? Yes. When something happens in Cursor, your agent can act in CrewForm too. This page covers both directions: Cursor's triggers and CrewForm's actions are listed here as well. ### ### Do I have to build a connector for CrewForm or Cursor? 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 CrewForm and Cursor 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.