Skip to main content
Connect Onsomble to JetBrains AI Assistant and you can ask it 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:
JetBrains AI Assistant does not yet support browser sign-in for a remote MCP server, so the connection authenticates with an Onsomble API key instead. When JetBrains adds sign-in, this page will cover it.

​
Add the server

1

Create an API key

In Onsomble, open Settings → Account → API Keys and create a key. Keys start with ons_ and are shown once at creation: see the API overview.
2

Add the server

In your IDE, open Settings → Tools → AI Assistant → Model Context Protocol, choose Add → Streamable HTTP, paste the address above, and name it Onsomble.
3

Paste the key

In the server’s HTTP headers, add Authorization with the value Bearer ons_your_api_key.
JetBrains’ own guide: Model Context Protocol (MCP).

​
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 assistant read the results like an analyst, install the Onsomble skills alongside the connection. 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.