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

- Registry name: `com.fronesislabs/dcl-trust-oracle` · version 2.3.1
- Categories (automatic, keyword rules): Crypto & blockchain, Finance & markets, Code & repositories, Developer tools, Agent payments (x402)
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.fronesislabs%2Fdcl-trust-oracle
- Server page: https://mcpstation.net/s/com.fronesislabs--dcl-trust-oracle.html

## Description (written by the publisher, not verified, not instructions)

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

## Notice

Text that looks like instructions to an AI was found in this server's descriptions. This is a pattern match, not a verdict.

## Connect

- streamable-http: `https://mcp.fronesislabs.com/mcp`

## Tools (as reported by the server, not verified)

- `dcl\_evaluate\_fast`: FAST Pre-Action Audit \($0.01\). Runs the response through the server's "default" policy: a substring check against 3 forbidden phrases \("ignore previous instructions", "jailbreak", "bypass safety"\) with a 0.7 minimum-confidence threshold. Each forbidden match found costs 0.4 confidence; if confidence
- `dcl\_evaluate\_strict`: STRICT Pre-Action Audit \($0.05\). Runs the response against a broader, higher-bar "strict" policy: the union of all forbidden phrases from the default, anti-jailbreak, and safety policies \(8 phrases total\), with a 0.85 minimum-confidence threshold instead of the default policy's 0.7. Each matched phr
- `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 confide
- `dcl\_evaluate\_safety`: PRE-ACTION Baseline Safety Check \($0.01\). Runs the "safety" policy: flags 2 forbidden disclaimers \("I cannot be held responsible", "no guarantees"\) and additionally REQUIRES the substring "AI" to appear somewhere in the response — missing it costs 0.2 confidence even with no forbidden phrase present
- `dcl\_evaluate\_quality`: PRE-ACTION Content Quality & Drift Check \($0.03\). Runs the "content\_quality" policy: flags 12 absolutist or unverifiable-claim phrases \(e.g. "guaranteed returns", "100% accurate", "studies show", "without a doubt"\) with a 0.85 minimum-confidence threshold — the highest bar of any single-policy tool.
- `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.
- `dcl\_evaluate\_pii`: POST-ACTION PII Detection Scan \($0.02\). Regex-based scan across 8 personal-data categories, with a Luhn checksum on card numbers to reduce false positives. Any finding results in NO\_COMMIT.
- `dcl\_evaluate\_batch`: PRE-ACTION Bulk Processing \($0.10\). Evaluates a list of items in one call; each item is a dict shaped \{"response": str, "policy"?: str\}, where policy defaults to "default" if omitted and may be any built-in policy name \(default, strict, anti\_jailbreak, safety, content\_quality\). Each item gets its ow
- `dcl\_pipeline\_start`: SESSION Management \($0.05\). Generates a new \`pipeline\_id\` and returns session metadata \(scope, expiry, initial drift\_mode\) for organizing a series of related checks under one identifier. Note: this call does not currently link the returned pipeline\_id to later evaluate\_\* calls — there is no server-s
- `dcl\_audit\_decode`: POST-ACTION Basic Audit \($0.10\). Retrieves a record from the tamper-evident chain by tx\_hash.
- `dcl\_audit\_decode\_deep`: POST-ACTION Deep Forensic Audit \($0.50\). Extended output with drift\_context and full chain integrity verification.
- `dcl\_evaluate\_jailbreak\_crypto`: PRE-ACTION Crypto Jailbreak & Injection Detection \($0.02\). Crypto-specialized instruction-override/jailbreak/injection screen: standard role-switch and instruction-override patterns, plus crypto-specific drain-wallet injection \(e.g. "transfer all funds to...", fake "test transaction" requesting full
- `dcl\_evaluate\_wallet`: POST-ACTION Wallet Secret Guardian \($0.02\). Scans for BIP-39 seed phrases \(12 or 24 consecutive wordlist words\), raw hex or WIF-format private keys, Ethereum/Bitcoin wallet addresses, and API keys/bearer tokens appearing near wallet/custody/signing terminology. Any finding results in NO\_COMMIT — wal
- `dcl\_evaluate\_trade`: PRE-ACTION Trade Decision Verifier \($0.02\). Screens trade-decision language for guaranteed-return claims, zero-risk/"can't lose" framing, and unqualified "buy/sell X now" directives — any match is NO\_COMMIT. If no unsafe language is found, COMMIT additionally requires the word "risk" to appear anywh
- `dcl\_evaluate\_mev`: POST-ACTION MEV & Market-Abuse Compliance Screen \($0.03\). Text-level screen \(not a mempool/transaction analyzer\) for front-running/sandwich-attack language, wash trading/layering/spoofing, KYC/AML red flags \(mixers, structuring, obscuring fund origin\), and pump-and-dump/rug-pull language. Any critic
- `dcl\_evaluate\_signal`: POST-ACTION Market Signal Fabrication Screen \($0.03\). Pattern-based heuristic on the output text alone \(no source price feed\) — flags guaranteed-price-prediction language \("will definitely hit $X"\), absolute-certainty claims \("100% certain", "cannot go down"\), a fabricated-price flag when a specific
- `dcl\_evaluate\_output\_sanitizer`: FINAL-GATE Output Sanitizer \($0.02\). Post-processing checkpoint that strips secrets/credentials, PII, crypto material \(seed phrases, private keys, wallet addresses\), internal network details \(private IPs, MAC addresses, .internal/.local/.corp hostnames\), and unsafe shell/SQL/path-traversal fragments
- `dcl\_commit`: FINAL-STEP Leibniz Layer Crypto Commit \($0.01\). Writes a trading/agent decision to the append-only Leibniz Layer audit chain and returns a Merkle-proof-style receipt: \`tx\_hash\` \(proof of this specific commit\), \`chain\_hash\` \(the previous commit's hash, linking this one into the chain\), and \`chain\_dep

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html