Technical checker · Model Context Protocol

Audit a website's MCP readiness

An MCP URL alone is not enough. Santos looks for a discoverable, interoperable interface whose tools are described precisely enough for an agent to select and use safely.

What the assessment covers

Advertised

Can an agent find the canonical MCP surface?

Interoperable

Does transport negotiation expose usable tools and typed schemas?

Safe to select

Are side effects, authorization, outputs, and limitations explicit?

Discovery and transport

The audit looks for MCP links in public documentation, machine-readable assets, registry evidence, and explicit endpoints, then assesses compatible transport and protocol negotiation without calling target business tools.

Tools, resources, and schemas

Useful servers provide deterministic tool descriptions, strict input schemas, declared outputs, structured content, and clear error behavior. Resource and prompt exposure is recorded when public evidence supports it.

Safety and authorization

Read-only, destructive, idempotent, and open-world behavior should be documented accurately. Protected servers should explain authorization discovery without leaking credentials into public metadata.

Frequently asked questions

Does every website need MCP or OpenAPI?

No. They matter when a site exposes callable services. Santos marks non-applicable checks instead of penalizing an informational website.

What is an Agent Readiness audit?

It checks the public technical signals that help agents find information, interpret structured meaning, and invoke applicable machine-readable capabilities.