Skip to main content
Glama

Moyan Audit — Agent Session Security Audit

moyan_checkup

Full deterministic security audit of an AI-agent session record (25 checks, three-level verdict: verified / unverified / unknown, per-check evidence). Provide the record as {profile, responses}, or as {session: {profile, responses}}, or as {question: ""}. Never include passwords, private keys, seed phrases, or production credentials — such input is rejected before execution.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "moyan_checkup"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileNoAgent profile object of the session record.
sessionNoWhole session record object ({profile, responses}).
questionNoSession record as a JSON string (same form as the HTTP checkup endpoint).
responsesNoResponses object of the session record, keyed by check id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must carry behavioral disclosure, and it does notably: it declares determinism, the exact number of checks, the 1-of-3 verdict taxonomy, per-check evidence output, and that credential/secret-bearing input is rejected before execution. It omits permission requirements and whether the operation is strictly read-only, but the behavioral picture is substantially richer than typical.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, purpose front-loaded, followed by the accepted input shapes and the safety note. Dense but every clause carries information; the long input-form sentence is justified by the ambiguity it resolves.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter nested tool with no output schema and no annotations, the description covers the essentials: what is audited, what the verdict looks like, and how to supply the record. Only the relationship to moyan_precheck and any required permissions remain uncovered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so per-dimension guidance sets the baseline at 3. The description does add real value the schema cannot express: it spells out that the inputs may be supplied as three alternative shapes ({profile, responses}, {session:{...}}, or {question: JSON string}), which the flat schema with additionalProperties does not encode.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('full deterministic security audit of an AI-agent session record') plus scope detail (25 checks, three-level verdict, per-check evidence). An agent can tell exactly what the tool produces. It stops short of naming the sibling moyan_precheck, so no explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description spends its guidance on HOW to supply input (three accepted shapes) but never says WHEN to pick this tool over moyan_precheck or what conditions make it inappropriate. Usage is implied by the audit framing only.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources