Skip to content
Primetra
All agents

Agent reference · Assistant

claude.ai

Claude calling your MCP server for a person from claude.ai, the desktop or the mobile app, always from Anthropic's cloud. Verified by Anthropic's published address or its sign-in; the product name comes from a header Anthropic sends.

Vendor
Anthropic
Agent type
AssistantThe assistant apps themselves, as they reach your site, your API or your MCP server.
Can be verified by
Can't be verifiedThe vendor publishes nothing a visit can be checked against. A visitor using this name can be named, never proven.
How sure we are
UnverifiedOnly third-party lists mention it. We name it, and never treat it as proven.
Last reviewed
Vendor documentation
platform.claude.com (opens in a new tab)

Tokens to look for

User-Agent tokens

No user-agent token is documented: its visits don't name it.

robots.txt tokens

No robots.txt token is documented for it.

Check a visitor claiming to be claude.ai

We've filled in its token. Paste the full User-Agent from your logs and the address it came from for a real answer.

Paste the full User-Agent header from your logs. A single token such as GPTBot works too.

Optional

IPv4 or IPv6, as your logs show it. Used only for this check and never stored. Without it, a claim can only come back as can't be verified.

What this means for your site

claude.ai is how people meet you inside an assistant. What it can read, and the tools it can call, shape what it says about you.

See whether AI agents can find your product, use it and, soon, pay for it.

Run the free agent-readiness check