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

> com.fronesislabs/dcl-trust-oracle — com-fronesislabs-dcl-trust-oracle. Use this tool when you need to ensure the integrity and compliance of AI outputs, particularly for large language models (LLMs) and agents. It provides a deterministic audit layer with policy checks, tamper-evident logging, and x402 compliance, solving problems related to trust and reliability in AI decision-making. Ideal for applications requiring transparent and accountable AI outputs, such as high-stakes decision support systems or regulated industries.

Canonical page: https://skillsregistry.net/skills/com-fronesislabs-dcl-trust-oracle  
JSON: https://api.skillsregistry.net/v1/skills/com-fronesislabs-dcl-trust-oracle

## Description

AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.

## Trust

- **Trust score (0–1):** 0.82
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 2.3.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-03

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.fronesislabs%2Fdcl-trust-oracle)
- **Repository:** <https://github.com/Fronesis-Labs/dcl-webhook>

## Use it

MCP endpoint published by the skill: `https://mcp.fronesislabs.com/mcp`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "com-fronesislabs-dcl-trust-oracle"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-fronesislabs-dcl-trust-oracle` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-fronesislabs-dcl-trust-oracle/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt