Systemores AI Agent & MCP Security Auditor

Live Turn Audit (Systemores System One)

systemores_audit_turn_live

Read-onlyIdempotent

Performs real-time (~250ms) operational and behavioral turn auditing using Systemores System One. Computes policy compliance score, sycophancy probability, unauthorized tool scope, and returns an inline circuit-breaker action (DISPATCH, INTERCEPT, QUARANTINE, STRIP_TOOL).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "systemPrompt": "<systemPrompt>",
      "userMessage": "<userMessage>"
    },
    "name": "systemores_audit_turn_live"
  }
}

Input Schema

Name	Required	Description
`userMessage`	Yes	The prompt or message sent by the user in this interaction turn.
`systemPrompt`	Yes	The behavioral blueprint, constraints, or security policies of the agent under audit.
`agentResponse`	No	The proposed text response or output from the agent.
`proposedToolCall`	No	Optional tool invocation or function call proposed by the agent (name and arguments).

Output Schema

Name	Required	Description	Default
`engine`	Yes
`status`	Yes
`tokens`	No
`metrics`	Yes
`verdict`	Yes
`latencyMs`	Yes
`circuitBreakerAction`	Yes
`autoRecoveryRecommendation`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Goes beyond the annotations by disclosing latency (~250ms), the four computed metrics, and the exact action vocabulary returned (DISPATCH, INTERCEPT, QUARANTINE, STRIP_TOOL), which tells the agent this tool can gate traffic without mutating anything. Consistent with readOnlyHint=true and destructiveHint=false. It does not explain what triggers each action level, which is the main remaining gap.

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

Conciseness5/5

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

Two dense sentences with no filler: capability and latency first, then the computed signals and return vocabulary. Every clause carries information an agent would need to select and interpret the tool.

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?

An output schema exists, so return structure needn't be explained, and annotations cover the safety profile; the description fills in the metrics and the action set. It is nearly complete for a four-parameter read-only evaluator, lacking only the criteria that map scores to each circuit-breaker action.

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 all four parameters are already documented in structured form and the baseline of 3 applies. The description adds the auditing dimensions being scored but no additional semantics for systemPrompt, userMessage, agentResponse, or proposedToolCall.

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 ('turn auditing') with concrete outputs: policy compliance score, sycophancy probability, unauthorized tool scope, and a circuit-breaker action. The 'turn'-level framing distinguishes it implicitly from graph-, tool-integrity-, and drift-oriented siblings, though no sibling is named explicitly.

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?

Usage is only implied — 'real-time' and 'inline circuit-breaker action' suggest this belongs in a live per-turn loop rather than batch analysis, which is a useful signal. However, the description never says when to prefer this over systemores_audit_agent_graph or systemores_audit_tool_integrity, nor any exclusions or prerequisites.

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

All Systemores AI Agent & MCP Security Auditor tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.