Keep the context when you export results.
Every rate comes back with its sample size and an interval, so you can interpret the percentage. Reads cost no credits.
- Read API and MCP serverLive
AI visibility API and MCP server
A read API and an MCP server, so analysts can pull results into their own scripts and anyone can ask Claude or ChatGPT “how did we do in Perplexity this month?”.
See it
Example data in a sample workspace.
GET /api/v1/projects/prj_123/metrics?engines=perplexity
Authorization: Bearer slk_••••
{
"data": { "engine": "perplexity", "k": 87, "n": 212,
"rate": 0.41, "ci": [0.35, 0.48] },
"meta": { "methodology": { "url": "/methodology" } }
}API & MCP
Every rate comes back with its sample size and an interval, so you can interpret the percentage. Reads cost no credits.
Keys are scoped, stored hashed and can be rotated, with a rate limit per key.
Connect the MCP server to Claude or ChatGPT and ask about your own results in plain words.
Details
Labels come from the same list our pricing page and app use. If it says Coming soon, it is not live yet.
| API and MCP | Live |
|---|---|
| API keys | Live |
| Status | Live |
Yes.
Reads are planned to cost no credits. Writes that change scheduled work use credits like the app does.
Paste your website. We find your market and category, ask each engine, and show you every answer.