Skip to main content
Connect Onsomble to Cursor and you can ask its agent about your AI discoverability while you work: how a brand is showing up in AI answers, what the AI is saying, and what to fix. The connection is one address:
You sign in to Onsomble the first time you connect, so no keys change hands. For a config committed to a project or a CI run, use an API key instead.

​
Add the server

1

Add a custom server

Open Settings → Tools & Integrations and choose Add custom MCP server. Paste the address above and name it Onsomble.
2

Sign in and approve

Cursor asks for approval before using a new connector. Sign in to Onsomble in the browser that opens and approve access.
Cursor’s own guide: Model Context Protocol.

​
Use it

Name Onsomble in your first message and name the Site you mean. A few to start with are on the overview. To make the agent read the results like an analyst, install the Onsomble skills alongside the connection.

​
API keys for scripts and CI

To share the connection through a committed config or run it unattended, authenticate with an Onsomble API key instead of signing in. Create one in Settings → Account → API Keys: see the API overview. Keys start with ons_ and are shown once at creation. Add the server to ~/.cursor/mcp.json for yourself, or .cursor/mcp.json in a project to share it:
Enable the server under Cursor Settings → MCP, then ask the agent about one of your Sites.
A committed config file must never contain the key itself. Keep project files to the server URL and inject the key from each developer’s local configuration, or use a personal config file instead.
Onsomble MCP can read results and, with the required permissions, change Clients, Sites, scan configuration and schedules. Starting a Scan uses scan allowance. Review and approve changes and scan runs before your assistant carries them out. In automated setups, keep confirmation enabled for write actions.