Claude Code How to use Cursor Agents with Claude Code
You want Cursor Agents inside Claude Code so it can launch agents to implement repository work, monitor cloud-agent runs, iterate on an agent's pull request, and collect agent artifacts and usage — without you copy-pasting between tabs. Here is the whole setup, once.
Create your Cursor Agents gateway
The gateway is the thing Claude Code connects to, and it is where you decide which Cursor Agents tools an agent may use. You create it once and every client reuses it.
-
Create an Arcade account
Sign up and open the dashboard. The free tier is enough to follow this through.
-
Create an MCP Gateway and select your Cursor Agents tools
In the dashboard, create a gateway and pick the Cursor Agents tools you want to expose. The gateway is what your client connects to, and it is where tool access is decided.
-
Copy your gateway URL
Every client below needs it.
https://api.arcade.dev/mcp/<YOUR-GATEWAY-SLUG>
Connect the gateway to Claude Code
-
Add the gateway as a remote HTTP MCP server
claude mcp add arcade --transport http "<YOUR_ARCADE_GATEWAY_URL>"
-
Verify it was added
claude mcp get arcade claude mcp list
-
Try it out
Open Claude Code in your project and ask it to use one of your Cursor Agents tools.
Full Claude Code guide in the docs steps verified 2026-08-13
Try these Cursor Agents prompts
Claude Code can now act on your Cursor Agents account. Click a prompt to copy it.
Control which actions the agent can take before it starts or changes cloud coding runs. Pair it with Contextual Access policies so an agent can inspect runs and artifacts without being allowed to launch, cancel, archive, or delete agents.
