Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Cursor Cloud Agent with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Create and manage Cursor cloud agents. spin up autonomous coding agents, track runs, monitor usage, and manage artifacts from any AI assistant.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 12 capabilities

The complete Cursor Cloud Agent capability set.

These are the exact actions your AI can choose when you ask it to work with Cursor Cloud Agent.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through Cursor Cloud Agent.

  1. 01

    Create run

    The run receives a prompt (required), optional images, optional MCP servers, and an optional mode override. Returns the run object with status and ID. Create a new run for an existing Cursor cloud agent

  2. 02

    Get agent

    Use this to check agent configuration or status. Get full metadata for a specific Cursor cloud agent

  3. 03

    Get agent usage

    Optionally filter by runId to get usage for a specific run. Get token usage statistics for a Cursor cloud agent

  4. 04

    Get me

    Use this to verify API key validity and identify the authenticated account. Get information about the authenticated Cursor API user

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through Cursor Cloud Agent.

  1. 05

    Get run

    Use this to check if a run completed, see its output, or inspect git branches it created. Get details and status of a specific Cursor cloud agent run

  2. 06

    List artifacts

    Use this to discover what files the agent created or modified. List all artifacts produced by a Cursor cloud agent

  3. 07

    List runs

    Supports limit and cursor for pagination. Returns items array with run summaries. List all runs for a specific Cursor cloud agent

  4. 08

    Unarchive agent

    This operation is idempotent. unarchiving an already-active agent succeeds without error. Restore an archived Cursor cloud agent. Idempotent operation

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through Cursor Cloud Agent.

  1. 09

    Archive agent

    The agent is no longer active but can be restored with unarchive_agent. This operation is idempotent. archiving an already-archived agent succeeds without error. Archive (soft delete) a Cursor cloud agent. Idempotent operation

  2. 10

    Cancel run

    This is a terminal cancellation. once cancelled, the run cannot be resumed. Use this when a run is taking too long or is no longer needed. Cancel a running Cursor cloud agent run. Terminal operation

  3. 11

    Create agent

    The agent receives a prompt (required), can be configured with a model (e.g. gpt-4.1, claude-sonnet-4-20250514, gemini-2.5-pro), optional repository URLs with starting refs, autoCreatePR flag, and mode (agent or plan). Returns the agent object and an initial run object. Create a new Cursor cloud agent with a prompt and optional repos, model, and mode

  4. 12

    List agents

    Supports limit (default 20, max 100), cursor for pagination, prUrl to filter by PR, and includeArchived (default true). Returns items array and nextCursor for pagination. List all Cursor cloud agents with pagination and filtering

Observed, not estimated

980ms average. Fast in production.

Cursor Cloud Agent is checked daily against the live service.

Daily averagePeak 1164ms
Aug 20Today
Fastest day
805ms
Slowest day
1164ms
14-day trend
Improving-9%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cursor Cloud Agent, so you can see the experience inside your AI.

It does not authenticate your account with Cursor Cloud Agent. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Cursor Cloud Agent Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_WJUsxIeBdLTUmOiGm9g0ZUKYn9WLxdIjkfcta731/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Cursor Cloud Agent capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "cursor-cloud-agent-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_WJUsxIeBdLTUmOiGm9g0ZUKYn9WLxdIjkfcta731/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Cursor Cloud Agent owners ask.

  • 01

    How do I get my Cursor API key?

    Go to the Cursor Dashboard → API Keys section to create or manage your API key. The key starts with crsr_ and can be either a user API key or a service account API key. Copy it and paste it into the API key field in the setup wizard. The key is sent as a Bearer token in the Authorization header for all API requests.

  • 02

    What are Cursor cloud agents?

    Cloud agents are autonomous coding agents that run in Cursor's managed environment. You give them a prompt describing what you want (e.g. 'Add a README file to this repo'), connect one or more repositories, and the agent works autonomously. reading code, making changes, and optionally creating pull requests. You can track run status, view results, and manage the agent lifecycle through the API.

  • 03

    Can cloud agents automatically create pull requests?

    Yes! When creating an agent, set the autoCreatePR flag to true and the agent will automatically create a pull request when it finishes its work. You can also filter agents by PR URL using the pr_url parameter in the list_agents capability to find agents associated with a specific PR.

  • 04

    Which models are supported by cloud agents?

    Cursor cloud agents support multiple AI models including gpt-4.1, claude-sonnet-4-20250514, and gemini-2.5-pro. You can specify the model when creating an agent using the model_id parameter. If no model is specified, Cursor uses its default model. The model determines which AI processes your agent's prompts and generates code changes.

  • 05

    How do I track the status of a run?

    Use the get_run capability with the agent ID and run ID to get the full status including the current state (running, completed, cancelled), duration in milliseconds, the result output, and git branch information. You can also use list_runs to see all runs for an agent. To stop a long-running run, use cancel_run. this is a terminal operation that cannot be undone.

  • 06

    Can I configure MCP servers for my agent runs?

    Yes. When creating a run with the create_run capability, you can pass an mcp_servers_json parameter containing a JSON array of MCP server configurations. This allows your cloud agent to access external capabilities and resources during the run, extending its capabilities beyond the default set of capabilities.

  • 07

    Are there rate limits on the Cloud Agents API?

    Yes, the Cursor Cloud Agents API enforces standard rate limiting. If you exceed the rate limit, the API returns an error and the engine surfaces the error message. For high-volume usage, consider spacing out requests and using pagination (limit and cursor parameters) when listing agents and runs. The get_agent_usage capability helps you monitor token consumption to stay within your plan's limits.

Explore

More in Developer Tools

Suggestions