Moyan Audit — Agent Session Security Audit
Server Details
Security audit of AI-agent session records: 25 checks, three-level verdict, per-check evidence.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
moyan_checkup (full 25-check audit of a structured session record) and moyan_precheck (free-text single-event pre-check) are mostly separable by input type and depth, but the boundary blurs because moyan_precheck silently escalates to the same full 25-check engine when a structured record is embedded. An agent could reasonably hesitate over which tool to call for a session record that also contains narrative context.
Both names share a stable moyan_ prefix and a parallel noun-style suffix (checkup / precheck), which reads predictably as a pair. Neither follows a verb_noun pattern and 'checkup' vs 'precheck' is a subtle distinction, but the convention itself is consistent.
Two tools is thin, though defensible for a narrowly scoped stateless audit engine where a full audit and a lightweight pre-check are the two natural entry points. There is little room to grow without either merging the pair or adding discovery/reporting helpers.
The core audit lifecycle (quick pre-check → full deterministic audit with verdict and per-check evidence) is covered, but there is no way to enumerate the 25 checks, retrieve check definitions, or obtain remediation guidance after a verdict. A batch/compare operation is also absent, leaving agents with dead ends once an audit is returned.
Available Tools
2 toolsmoyan_checkupAInspect
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.
Inputs: profile, session, question, responses.
moyan_precheckAInspect
Single-event security pre-check from a free-text incident description (deterministic feature pre-check; patterns reported by the submitter are marked unverified, unaddressed categories unknown). If the description embeds a structured session record JSON, the full 25-check engine runs instead. Never include passwords, private keys, seed phrases, or production credentials — such input is rejected before execution.
Inputs: text (required), title, context, endpoint.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI agent security audit: red-team probes plus missing-guardrail review with fixes.
LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails
LLM agent security scan: injection, jailbreak, tool abuse probes plus guardrail audit.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceLocal security layer for AI coding agents: MCP policy proxy, kernel sandbox, tamper-evident audit logMIT
- AlicenseAqualityCmaintenanceSecurity co-pilot for AI agents. Scans for vulnerabilities like prompt injection, infinite loops, and token bombing in AI Agents, audits MCP servers, verifies AGENTS.md governance, and generates EU AI Act compliance reports.10159 npm3Apache 2.0
- AlicenseAqualityDmaintenanceSecurity scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows.864 npmMIT
- FlicenseNot gradedqualityDmaintenanceLogs AI agent actions, computes reliability scores, generates audit reports, detects anomalies, and estimates risk to ensure agent accountability.-
Glama MCP Gateway
Add one secure layer between your agents and this server.