CrawlCheck Skip to content

Menu

How it works

For agents

Quickstart: ask before you act

MCP, curl, Python, OpenAI Agents, Claude tool use, LangChain

Every endpoint, with a worked example from production

Resolve protocol

The signed answer: what it holds, how to verify it

SDKs: npm and PyPI

Typed clients, the offline verifier, conformance fixtures

Capability registry

What sites declare agents can do, and what was verified

How each named agent behaves on sites, from verified requests

Every finding the measurement can raise, with its revision

The Ed25519 keys every answer is signed with

Before you act

One signed answer, no key.

Read, cite, connect or transact: ask first, verify the receipt offline, keep it with the action.

Start in a minute

For sites

The checks behind the audit, one at a time

Is your business record right where agents look?

Compare two sites

Two domains, side by side, same measurement

What search and answer engines read from a video

Browser extension

The second vantage point: from your own address, after JavaScript

The record on your phone, with receipts

Your site

Measured as agents see it.

A free A–F audit with every defect named, no account. Fix it, then prove it held.

Learn

Findings from the measurement, with the numbers

Every term the product uses, defined

Who sends each agent, what it reads, how to verify it

Evidence

The public census and the daily snapshot, CC BY 4.0

Proof and timestamps

How every record is sealed and anchored

SEO and AI tools, measured

The vendors that measure sites, measured by the same rules

Registry: media kits, llms.txt, entity graphs

Verified machine-readable profiles of real organisations

Pricing Sign in

MCP · operators

Verify, monitor and prove your MCP endpoint

Everything CrawlCheck holds about one MCP endpoint, the proof list to work down, live checks you can run now, and the badge that shows clients it is watched.

What you get

Verify	Registry listing, handshake outcome, 14-day availability and time to answer, tool-list drift, shadowing and the auth audit, from CrawlCheck’s own observations. Run the poisoning scan, auth audit and lockfile live from this page.
Monitor	On a paid plan CrawlCheck probes your endpoint every 15 minutes and alerts on downtime, a changed tool list and poisoning findings.
Prove	Prove control of your domain, publish the monitor as verified, and embed the badge. The signed record at /api/v1/mcp/operator is what a client or reviewer can check.

No tool is ever called. Every MCP server CrawlCheck observes: MCP registry · reliability index · lockfile spec.