Connect Cursor to Contro1

Who this is for

The AI code editor's agent, on your own computer. For: Cursor. Acts as: The Cursor agent itself. Credential: A key in the Contro1 service on the computer.

Cursor connects as its own agent with one command, which adds the Contro1 MCP server for company apps. Signing Cursor in as you instead still works, as an alternative.

Every way to connect an agent

Connect Cursor

Cursor on this computer becomes one Contro1 agent, named "Cursor on <computer name>", with you as its accountable owner, the same way Claude Code does. Its key stays in the Contro1 service on the computer. connect also adds the Contro1 MCP server to ~/.cursor/mcp.json, so every project has it, and everything Cursor does through it is recorded as that agent.

Adding the remote address https://api.contro1.com/api/centcom/mcp directly in Cursor does not work today. Cursor's sign-in returns to a cursor:// address, which Contro1 refuses because the code would only reach the computer that opened the link. Use contro1 connect cursor.

Connect Cursor, step 1: Install the Contro1 CLI

Once per computer. The installer downloads the contro1 program from its official GitHub releases. You can read it first at https://contro1.com/install.sh (PowerShell: https://contro1.com/install.ps1).

curl -fsSL https://contro1.com/install.sh | sh
contro1 --version

irm https://contro1.com/install.ps1 | iex
contro1 --version

What you should see: The installer ends with "Installed contro1 to <folder>", and contro1 --version prints "contro1 version 0.2.29" or later. On Windows, if contro1 is not found, open a new terminal: the installer added it to your PATH.

Connect Cursor, step 2: Sign in to Contro1 on this computer

A browser opens on a Contro1 approval page. Approve it with your Contro1 account.

contro1 auth login

What you should see: "Logged in as you@company.com (Org: <your organization>)".

Connect Cursor, step 3: Connect Cursor

connect lists every change before it makes any: the local Contro1 service, and the contro1 entry it adds to ~/.cursor/mcp.json. Every other server and setting in that file is kept, and a copy of the file is saved next to it first.

At "Continue? [y/N]" type y. It then asks once for administrator approval, to register the agent key with the Contro1 service.

contro1 connect cursor

What you should see: The list includes "Register the Contro1 MCP server with Cursor, for every project (other servers are kept; a backup is made first)" with the entry it adds, "contro1": {"type":"stdio","command":"<full path to contro1>","args":["mcp","serve","--agent","cursor@<id>"]}, then "Continue? [y/N]" and the administrator prompt.

Connect Cursor, step 4: Approve the agent as its owner, then open a new Cursor window

connect prints an approval link and waits up to 11 minutes. Open it and approve. connect then writes the MCP entry and calls the server through the agent's own endpoint. A Cursor window that was already open loads the new server in a new window.

What you should see: "Approve at https://contro1.com/... Code: ABCD-EFGH", then "Approved.", "Registered the Contro1 MCP server with Cursor (~/.cursor/mcp.json)." and "MCP connected: N actions available." In Cursor Settings, the MCP section (Tools & MCP in recent versions) lists contro1 as enabled.

Connect Cursor, step 5: Check every line

doctor checks the Contro1 service, the agent's private endpoint, an approval round trip (a preview, nothing is created), that the contro1 entry in ~/.cursor/mcp.json runs this agent, and a live MCP call.

contro1 doctor cursor

What you should see: The first line is "Contro1 doctor: cursor is connected", and every check under it starts with ✓, including "MCP server for cursor@<id>: contro1 runs contro1 mcp serve as cursor@<id>."

Connect Cursor, step 6: Try it

Open a new Cursor agent chat and ask: "Who am I in Contro1?"

What you should see: Cursor calls the whoami tool, which names the agent, "Cursor on <computer name>", and you as its owner. Ask it to list the Actions it can use, and it calls list_actions.

Connect Cursor, step 7: Alternative: sign Cursor in as you (acts as you)

Only if you want Cursor to act as you rather than as its own agent: everything it does is then recorded as yours, and it can do what you can. Sign the MCP connection in, then add the entry yourself, without --agent.

It shows a code and opens the approval page. You can approve on this computer or on any other device, such as your phone. On the page, check that "Run Actions as you" is ticked, then press Approve.

contro1 mcp login --execute

{
  "mcpServers": {
    "contro1": {
      "command": "contro1",
      "args": ["mcp", "serve"]
    }
  }
}

What you should see: "To connect, open this address on any device and approve: https://contro1.com/connect-app and enter the code: ABCD-EFGH". After you approve: "MCP connected for profile default (mcp:whoami, ..., mcp:actions:execute)." and "See or disconnect it anytime in Contro1: Settings > Connected apps." whoami in Cursor then names you.

Give it something to do

A connected agent starts with nothing. It can ask people for approval and report what it did. To use an application such as Gmail, two things happen in Contro1:

• Apps: an administrator turns the application on for the organization and chooses which of its Actions are allowed. That alone gives no agent a tool.
• Access: a person opens the agent, connects the account it should use (a shared team account, or their own), ticks the Actions it may run, and presses Save. People can do this for their own agents, within what the organization allows.
• A personal account, such as your own mailbox, is always used on your behalf. When you are the agent's owner and give it your own account in Access, that is recorded as you letting it act for you. Anybody else whose account it should use turns that on for the agent in Access themselves.
• The agent's page shows a "Get it working" card with three steps: Connected to Contro1, Can do something, Did something. It always shows the next one to do, and it disappears once all three are done.

Action Gateway: apps and access

When something does not work

Frequently asked questions

Is there a contro1 connect for Cursor?

Yes. contro1 connect cursor makes Cursor on this computer its own agent, with you as its owner and its key in the Contro1 service, and adds the Contro1 MCP server to ~/.cursor/mcp.json. Signing in as you with contro1 mcp login --execute and a plain contro1 mcp serve entry still works; Cursor then acts as you.

How do I disconnect Cursor?

Run contro1 disconnect cursor. It revokes the agent in Contro1, removes it from the Contro1 service on this computer, and asks before removing the contro1 entry from ~/.cursor/mcp.json (--yes removes it without asking). The agent and its history stay in Contro1.

Why can I not add the Contro1 URL directly in Cursor?

Cursor's sign-in sends the authorization code to a cursor:// address on the same computer. Contro1 refuses loopback and private-scheme addresses, because the person approving is often on a different device. The local server signs in with a code instead, which works from any device.

Related resources