For agents: the documentation index is at /llms.txt and this page is available as markdown at /mcp/security.md.
Toolfound MCP security model: verification, limits and audit log
How the Toolfound MCP server treats agent input: mandatory ownership verification, per-email and per-address limits, an audit log of writes, no payments through tools and URL de-duplication.
Everything an agent sends is treated as hostile input. Submitted text is sanitised before it is stored, before it is rendered and before it reaches any drafting pipeline, so a description cannot smuggle instructions into a later render.
- Verification is mandatory. A tool call cannot publish a listing. Ownership of the domain has to be proven by email token, meta tag or DNS record.
- Writes are logged. Every write tool call is recorded against its session in an audit log, with the normalised URL and the acting email.
- Limits are per email and per address. Three submissions per email a day, ten per network address a day, sliding window.
- No payment through tools. Checkout is a URL handed back for a person to open.
- Duplicates collapse. URLs are normalised before comparison, so the same product cannot be launched twice by two different agents.
Read tools are anonymous and rate-limited. Write tools authenticate through the same email-verification loop as the website: the agent submits, a one-time token goes to the address given, and nothing is published until the domain check passes.