DCL Trust Oracle — AI/LLM Output Audit (x402 MCP)

Jailbreak Detection Check

dcl_evaluate_jailbreak

PRE-ACTION Instruction Adherence Check ($0.02). Runs the "anti_jailbreak" policy: a substring check against 6 forbidden phrases ("ignore previous instructions", "jailbreak", "bypass safety", "pretend you are", "act as if", "DAN") with a 0.8 minimum-confidence threshold — each match costs 0.4 confidence. Returns COMMIT if no phrase matches and confidence stays at or above 0.8, otherwise NO_COMMIT with reason listing the matched phrase(s). Use this as a targeted, cheaper check when the concern is specifically prompt-injection / persona-hijack risk; use dcl_evaluate_strict instead when you also want safety- and default-policy phrases covered in the same call.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`agent_id`	Yes	Identifier of the agent that produced the response.
`response`	Yes	The agent or LLM response text to check for jailbreak attempts.

Output Schema

TableJSON Schema

Name	Required	Description
`reason`	Yes	Human-readable explanation of why the verdict was reached.
`tx_hash`	Yes	Hash of this record in the tamper-evident audit chain.
`verdict`	Yes	COMMIT if the response passed policy checks, otherwise NO_COMMIT.
`seal_text`	Yes	Human-readable Leibniz Layer verification seal.
`timestamp`	Yes	Unix timestamp when this record was sealed.
`confidence`	Yes	Confidence score of the verdict, from 0.0 to 1.0.
`drift_mode`	Yes	Current drift status: NORMAL, WARNING, ESCALATION, or BLOCK.
`input_hash`	Yes	Hash of the evaluated response (raw content is never stored).
`verify_url`	Yes	Public URL to independently verify this seal.
`chain_index`	Yes	Sequential index of this record in the audit chain.
`drift_score`	Yes	Z-score measuring deviation of the recent commit rate from baseline.
`policy_version`	Yes	Version of the policy that was applied.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 6, 2026

removedInput schema / properties / payment_id

Removed value: -{
-  "default": "",
-  "description": "Optional payment identifier returned by a previous call when payment is required",
-  "title": "Payment Id",
-  "type": "string"
-}

First observedAug 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

The description discloses the exact mechanism: substring check, the six forbidden phrases, the 0.8 confidence threshold, the 0.4 per-match cost, and the COMMIT/NO_COMMIT outcomes with a reason. This far exceeds what the annotations provide and leaves no ambiguity about behavior.

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?

Dense but every clause earns its place: cost, policy, threshold, phrases, outcomes, and routing to the sibling alternative are all present without fluff. The core action is front-loaded, so an agent immediately understands what the tool does.

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

Completeness5/5

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

Covers decision criteria, alternative tool routing, return outcomes, and pricing. With an output schema present, nothing an agent needs in order to invoke this correctly is missing.

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 the baseline is 3. The description adds algorithmic context but does not enrich the meaning of the two parameters beyond what their schema descriptions already state.

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

Purpose5/5

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

The description uses a specific verb ('Runs the anti_jailbreak policy') and names the exact detection scope: a substring check against six forbidden phrases. It explicitly distinguishes itself from dcl_evaluate_strict, so an agent can tell the tools apart without opening either schema.

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

Usage Guidelines5/5

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

The description explicitly states when to use this tool ('when the concern is specifically prompt-injection / persona-hijack risk') and names the alternative for broader coverage (dcl_evaluate_strict). This is textbook usage guidance with both a condition and an alternative.

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

All DCL Trust Oracle — AI/LLM Output Audit (x402 MCP) 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.