Skip to content

Scoring rules

61 published checks, grouped by what they inspect. 5 critical failures can force a block.

Transport security · 10

How the server is reached on the wire. Covers TLS and protocol-level confidentiality of probe traffic.

Endpoint hygiene · 3

Tool surface risk · 20

What an agent could do if it trusted every advertised tool. Covers destructive actions, credential disclosure, code execution, filesystem mutation, PII handling, prompt-injection-shaped input fields, and injection-bearing tool descriptions — i.e. the agent-specific threat surface, not just generic verb risk.

Schema quality · 5

Whether the tool surface is reviewable without invoking it. Tools without input schemas force agents to guess argument shapes; tool names that aren't plain ASCII identifiers confuse logging and allow-listing.

MCP discovery posture · 3

Metadata transparency · 10

Whether the server identifies itself and documents its tools — and whether the advertised identity matches the wire identity (cert CN/SAN, hostname). Operators need a stable name, a version, and an internally consistent identity claim to perform any kind of audit.

Exposure minimization · 1

Whether the server keeps its surface small. Large, sprawling tool sets expand the agent's blast radius and are harder to review.

Auth discovery posture · 9

When authorization is required, whether the server cooperates with the standards-based discovery chain — RFC 9728 protected resource metadata, RFC 8414 authorization server metadata, validated issuers, and safe grant types.