Sign in Book a demo
Back to Tools
Developer Tools API Key
Build Your Agent View Documentation
cursor-agents logo

Cursor Agents MCP Tools for AI Agents

Let an agent launch Cursor cloud agents, follow runs, send follow-up prompts, download artifacts, and manage agent lifecycles.

Available Tools

20 tools available in this integration

CursorAgents.ArchiveAgent

Archive a cloud agent so it stops accepting new runs (reversible).

CursorAgents.CancelRun

Cancel an active run; cancelling an already-terminal run returns an error.

CursorAgents.DeleteAgent

Permanently delete a cloud agent.

CursorAgents.DownloadArtifact

Get a time-limited download link for one uploaded artifact file.

CursorAgents.GenerateArtifactUrl

Get a time-limited download link for one uploaded artifact file.

CursorAgents.GetAgent

Get a cloud agent's configuration and latest run pointer.

CursorAgents.GetAgentUsage

Get token usage for an agent, summed and broken down per run.

CursorAgents.GetRun

Get a run's current status, and its result, branches, and PR once terminal.

CursorAgents.LaunchAgent

Launch a Cursor cloud agent on a repository or named environment.

CursorAgents.ListAgents

List your cloud agents, newest first.

CursorAgents.ListArtifacts

List the artifact files a cloud agent explicitly uploaded.

CursorAgents.ListModels

List the LLM models available to launch a cloud agent with.

CursorAgents.ListRepositories

List every GitHub repository Cursor can reach, as repository urls.

CursorAgents.ListRuns

List an agent's runs, newest first.

CursorAgents.RestoreAgent

Restore an archived cloud agent to active.

CursorAgents.SendFollowupRun

Send a follow-up prompt to an existing agent, starting a new run.

CursorAgents.StartAgent

Launch a Cursor cloud agent on a repository or named environment.

CursorAgents.StartRun

Send a follow-up prompt to an existing agent, starting a new run.

CursorAgents.UnarchiveAgent

Restore an archived cloud agent to active.

CursorAgents.WhoAmI

Return the Cursor account the API key authenticates as.

Working directly against the raw API? 7 more tools in the Cursor Agents API server →

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "launch a coding task on the payments repository, run the tests, and return the pull request." Arcade picks the right Cursor Agents actions without guessing repository URLs, agent IDs, or run IDs.

Up to 100x fewer tokens

Cursor Agents listings return compact agent, run, repository, model, and artifact metadata first, while full run results and artifact files are fetched only when needed, so the agent avoids loading every run into context.

Complete the workflow end to end

Find a reachable repository, choose a model, launch the agent, monitor its run, and collect the pull request or artifact through one toolkit designed around the complete coding task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Cursor Agents

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Cursor Agents, you can implement some of these policies:

Access when tools are listed for a user
  • Hide CursorAgents.DeleteAgent from agents unless the roles your IDP marks as platform administrators are active, so ordinary automation cannot permanently remove a cloud agent.
  • Restrict CursorAgents.ArchiveAgent to owners of the affected agent, so a routine coding agent cannot stop another team's agent from accepting new runs.
  • Deny CursorAgents.UnarchiveAgent to agents outside your release-operations role, so an archived agent cannot resume work without an authorized operator.
  • Hide CursorAgents.RestoreAgent from agents unless the roles your IDP marks as agent owners are active, so routine automation cannot reactivate another team's archived worker.
  • Restrict CursorAgents.StartAgent to agents operating under your repository-maintainer role, so unreviewed automation cannot launch work against repositories it should not modify.
  • Deny CursorAgents.StartRun to agents without your approved automation role, so an agent cannot direct an existing cloud worker to perform unsanctioned follow-up work.
Pre-execution before each tool call
  • Require human approval before CursorAgents.LaunchAgent runs against a production repository or named environment, so an agent cannot start code changes in production unprompted.
  • Block CursorAgents.CancelRun for runs owned by another team or marked release-critical, so an agent cannot interrupt a deployment or discard another team's active work.
  • Require human approval before CursorAgents.SendFollowupRun sends a prompt that requests changes to a protected branch, so follow-up automation cannot direct production code changes without review.
  • Require human approval before CursorAgents.RestoreAgent runs for an agent tied to a production repository, so archived production automation cannot resume without an operator's review.
  • Block CursorAgents.StartAgent when the target repository is outside your approved repository allowlist, so an agent cannot begin work in an unapproved codebase.
  • Refuse CursorAgents.StartRun when its prompt asks the worker to expose credentials, tokens, or private source in an artifact, so follow-up automation cannot turn sensitive data into a downloadable file.
Post-execution after the tool returns
  • Deny the output of CursorAgents.DownloadArtifact for artifacts from production repositories, so the model cannot receive time-limited links to private build files or generated credentials.
  • Redact secrets, access tokens, and customer data from the result and pull-request fields returned by CursorAgents.GetRun before they reach the model.
  • Strip private repository URLs from CursorAgents.ListRepositories results for agents without your repository-discovery role, so the model cannot map repositories it is not authorized to inspect.
  • Deny the output of CursorAgents.GenerateArtifactUrl for artifacts containing credentials, access tokens, or customer data, so the model cannot receive time-limited links to sensitive files.

How to use Cursor Agents with your agent

Configure one shared API key, connect your MCP client, and give an agent an authenticated path to launch and monitor cloud coding runs.

Your questions, answered

A Cursor Agents MCP server exposes Cursor cloud-agent operations as structured tools an AI agent can call through the Model Context Protocol. It can launch agents on reachable repositories or environments, monitor runs, inspect results, and retrieve uploaded artifacts.

Cursor Agents does not provide a first-party MCP server in this integration. Arcade exposes the Cursor Agents API through an MCP gateway and adds brokered authentication, approval policies, response redaction, and access controls that work across supported clients.

Arcade agents can list reachable repositories, available models, cloud agents, runs, and artifacts; launch agents; send follow-up runs; inspect run results, branches, and pull requests; cancel runs; download uploaded artifacts; archive or restore agents; and permanently delete agents.

This integration uses one shared API key or secret configured once. The key determines the Cursor account, repositories, environments, models, agents, runs, and artifacts the agent can reach; no per-user OAuth scopes are described here.

No. Users do not connect separate Cursor Agents accounts through this integration. A shared API key or secret is configured once, brokered by Arcade, and used for calls within the access granted to that credential.

Yes. Contextual Access policies can require human approval before launching an agent, sending a follow-up run, canceling a run, archiving an agent, or permanently deleting one. The call proceeds only after the policy's conditions are satisfied.

Arcade proxies Cursor Agents API calls and does not persist your content as part of normal tool execution. The shared credential is brokered and stored encrypted at rest, and the model never receives it.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the configured authorization remains valid. If the shared API key or secret is revoked, rotated, or can no longer be used, calls stop until the credential is reconnected or replaced.

Cursor Agents API rate limits and any account, repository, or model quotas still apply through Arcade. Calls that exceed those limits can fail or be delayed according to Cursor's service behavior; no separate Cursor Agents limits are specified here.

Ready to actually ship your agent?

Connect your agent to Cursor Agents with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Cursor Agents Quickstart