Conseto speaks MCP, so the assistant you already use can read this site's traffic, consent and audit data directly. No export, no copy and paste, no second tool to learn.
MCP (Model Context Protocol) is how an AI assistant plugs into a data source. You paste one address and one key into Claude or Cursor, and from then on you ask questions in your own words. Conseto answers from the same numbers the dashboard shows, because it runs the same query underneath.
Read only. An agent can look at your data, never change it, never delete it.
One key, one site. A key opens exactly one project and nothing else.
Bot traffic is already excluded, and every answer says how much was removed.
Open Settings, Projects, the site you want, and find Agent access (MCP).
Create a key. It is shown once, so copy it before you close the page.
Paste one of these into your tool.
claude mcp add --transport http conseto https://api.conseto.io/mcp \
--header "Authorization: Bearer cmk_YOUR_KEY"{
"mcpServers": {
"conseto": {
"type": "http",
"url": "https://api.conseto.io/mcp",
"headers": {
"Authorization": "Bearer cmk_YOUR_KEY"
}
}
}
}{
"mcpServers": {
"conseto": {
"url": "https://api.conseto.io/mcp",
"headers": {
"Authorization": "Bearer cmk_YOUR_KEY"
}
}
}
}Web connectors on claude.ai are not supported yet, they require OAuth sign in. We are building it.
Five tools. The agent picks between them on its own, you never name them.
Lists everything this project can be asked about: sources, metrics with their units, dimensions with their value formats, and how far back your plan keeps data. The agent calls this first so it can never invent a metric.
The numbers: any metric, broken down by up to two dimensions, over any period, as a time series or against the previous period. Returns the rows and the exact SQL behind them.
Individual records instead of totals: one visitor's path, one session, one order. For when the aggregate is not the answer.
The most common values of a dimension, with counts. This is how the agent learns that your channels are called Direct and Organic Search before it filters on them.
Which project this key opens, its plan and its retention window.
Written the way you would actually say them.
How many people came from ChatGPT in the last 30 days?
What is our consent rate, split by legal regime?
Which Google queries rank in the top 3 but get no clicks?
Compare mobile and desktop sessions to the same month last year.
Show me every page that lost traffic this week.
What did the last security scan find?
Business and Enterprise plans. Free and Starter do not include MCP.
60 requests per minute per key. An agent doing normal work stays far below it.
Questions reach as far back as your plan retains data. Older ranges are trimmed to what exists, not refused.
Up to 10 active keys per project, so each machine can have its own.
Read only, at the protocol level. There is no tool that writes, and no way to ask for one.
A key is bound to one project. It cannot see your other sites and cannot see anyone else's.
We store only a fingerprint of the key, never the key. That is why it is shown once.
Revoke a key in settings and it stops working immediately, without touching the others.
Raw event parameters are not available over MCP. They are free-form data written by your own site, so we cannot promise what is inside them.
Kovrin is the first thing we connected to Conseto this way, and it connects exactly like your agent does: same address, same kind of key, same five tools. Conseto measures, and anything that wants those numbers asks for them here.
MCP is included in Business. Create a key and connect in under a minute.