AI & Machine Learning

fronesislabs.com

Provides pre-action audits and evaluations for AI outputs, including safety, quality, jailbreak resistance, and instruction adherence.

x402 supported1 endpoint18 known toolsFirst detected August 13, 2026Last detected August 13, 2026

ENDPOINT 1

https://mcp.fronesislabs.com/mcp

No auth detected

MCP server metadata

Name: DCL Trust Oracle
Version: 2.3.1

Capabilities

experimentalpromptsresourcestools

Server instructions

DCL Trust Oracle is a deterministic AI audit layer, natively integrated with the Model Context Protocol (MCP), that evaluates LLM and agent outputs against configurable policies before and after action. Every verdict is written to a tamper-evident, hash-chained audit log that stores only cryptographic metadata — never raw content — enabling privacy-first, post-action forensic review. The server exposes Jailbreak detection (instruction adherence checks), Quality and drift evaluation, and baseline Safety checks alongside fast and strict pre-action audit tiers. Tool calls are metered and settled via the x402 micropayment protocol (USDC on Base), letting autonomous agents pay per-call without any account setup. Use these tools to gate risky agent actions, batch-evaluate responses, and cryptographically verify the integrity of past decisions.

Known tools 18

dcl_evaluate_fast

FAST Pre-Action Audit ($0.

Inferred read-only

dcl_evaluate_strict

STRICT Pre-Action Audit ($0.

Inferred read-only

dcl_evaluate_jailbreak

PRE-ACTION Instruction Adherence Check ($0.

Inferred read-only

dcl_evaluate_safety

PRE-ACTION Baseline Safety Check ($0.

Inferred read-only

dcl_evaluate_quality

PRE-ACTION Content Quality & Drift Check ($0.

Inferred read-only

dcl_evaluate_secrets

POST-ACTION Secret & Credential Leak Scan ($0.

Potential side effects

dcl_evaluate_pii

POST-ACTION PII Detection Scan ($0.

Potential side effects

dcl_evaluate_batch

PRE-ACTION Bulk Processing ($0.

Inferred read-only

dcl_pipeline_start

SESSION Management ($0.

Inferred read-only

dcl_audit_decode

POST-ACTION Basic Audit ($0.

Potential side effects

dcl_audit_decode_deep

POST-ACTION Deep Forensic Audit ($0.

Potential side effects

dcl_evaluate_jailbreak_crypto

PRE-ACTION Crypto Jailbreak & Injection Detection ($0.

Inferred read-only

dcl_evaluate_wallet

POST-ACTION Wallet Secret Guardian ($0.

Potential side effects

dcl_evaluate_trade

PRE-ACTION Trade Decision Verifier ($0.

Potential side effects

dcl_evaluate_mev

POST-ACTION MEV & Market-Abuse Compliance Screen ($0.

Potential side effects

dcl_evaluate_signal

POST-ACTION Market Signal Fabrication Screen ($0.

Potential side effects

dcl_evaluate_output_sanitizer

FINAL-GATE Output Sanitizer ($0.

Inferred read-only

dcl_commit

FINAL-STEP Leibniz Layer Crypto Commit ($0.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.dcl-trust-oracle]
url = "https://mcp.fronesislabs.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "dcl-trust-oracle": {
      "type": "http",
      "url": "https://mcp.fronesislabs.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: dcl-trust-oracle
Remote MCP URL: https://mcp.fronesislabs.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "dcl-trust-oracle": {
      "url": "https://mcp.fronesislabs.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "dcl-trust-oracle": {
      "type": "http",
      "url": "https://mcp.fronesislabs.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "dcl-trust-oracle",
  "transport": "streamable-http",
  "url": "https://mcp.fronesislabs.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.