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

Secret & Credential Leak Scan

dcl_evaluate_secrets

POST-ACTION Secret & Credential Leak Scan ($0.02). Regex-based scan across 8 categories (API keys, cloud credentials, tokens/JWTs, private keys, DB URLs, connection strings, env assignments, webhook secrets, internal endpoints with auth). Any finding results in NO_COMMIT.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`agent_id`	Yes	Identifier of the agent that produced the response.
`response`	Yes	The text to scan for exposed API keys, tokens, private keys, DB URLs, and other credentials.

Output Schema

TableJSON Schema

Name	Required	Description
`tx_hash`	Yes	Hash of this record in the tamper-evident audit chain.
`verdict`	Yes	COMMIT if nothing was found, otherwise NO_COMMIT.
`findings`	Yes	All matches found. Empty list if verdict is COMMIT.
`seal_text`	Yes	Human-readable Leibniz Layer verification seal.
`timestamp`	Yes	Unix timestamp when this record was sealed.
`input_hash`	Yes	Hash of the scanned text (raw content is never stored).
`risk_score`	Yes	0.0-1.0 risk score based on number and severity of findings.
`verify_url`	Yes	Public URL to independently verify this seal.
`chain_index`	Yes	Sequential index of this record in the audit chain.
`detection_count`	Yes	Number of findings.
`categories_clear`	Yes	Categories with no findings.
`categories_checked`	Yes	All checklist categories that were scanned.

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

A4/5.0

Behavior4/5

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

Beyond annotations, the description discloses the detection method ('regex-based'), the category scope, the cost, and the gate behavior ('Any finding results in NO_COMMIT'). It does not explain what happens on a clean scan or whether findings are severity-ranked, but the output schema and simple annotations reduce the severity of that omission.

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?

The description is compact and information-dense: two sentences convey timing, cost, method, target categories, and outcome. There is no filler, and the most important usage constraint is front-loaded with 'POST-ACTION'.

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 tool with only two string parameters, complete schema descriptions, and an output schema, the description covers purpose, timing, and behavioral outcome adequately. It could be more explicit about when to choose this tool over sibling evaluate tools and what a no-finding result returns, but those are minor gaps.

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%, with clear descriptions for both 'response' and 'agent_id'. The description confirms that the response is the text to scan and adds credential categories, but it does not need to provide further parameter-level semantics. Baseline 3 is appropriate because the schema already carries the semantic load.

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 clearly names a specific operation ('scan') and resource ('secrets and credentials'), and further specifies the scope with concrete categories such as API keys, cloud credentials, tokens/JWTs, and private keys. This differentiates it from sibling evaluate tools like dcl_evaluate_pii or dcl_evaluate_safety.

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 'POST-ACTION' prefix and 'Any finding results in NO_COMMIT' give useful pipeline context, indicating the tool runs after an action and gates the commit. However, there is no explicit guidance about when to prefer this tool over sibling secrets-related or other evaluate tools, so the agent must infer selection from the name.

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.