mcp server · observation history
com.fronesislabs/dcl-trust-oracle
Observed since 2026-09-03, last seen 2026-09-25. Currently reachable. 0 contract changes recorded, 0 of them breaking.
What this server does
In its own words. Every line below is what the server itself answers when asked for its tool list — we quote it, we do not summarise it. The wording is the operator's, not ours.
| Tool | What the server says it does |
|---|---|
dcl_audit_decodeneeds: tx_hash | POST-ACTION Basic Audit ($0.10). Retrieves a record from the tamper-evident chain by tx_hash. |
dcl_audit_decode_deepneeds: tx_hash | POST-ACTION Deep Forensic Audit ($0.50). Extended output with drift_context and full chain integrity verification. |
dcl_commitneeds: agent_id, decision | 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_depth` (this commit's position in the chain). Unlike the evaluate_* tools, this call has no pass/fail v |
dcl_evaluate_batchneeds: agent_id, items | 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 own independent COMMIT/NO_COMMIT verdict via the same logic as the matching single-item evaluate_* too |
dcl_evaluate_fastneeds: agent_id, response | 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 falls below 0.7, or any match is found, the verdict is NO_COMMIT and `reason` lists which phrase tr |
dcl_evaluate_jailbreakneeds: agent_id, response | 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 â each match costs 0.4 confidence. Returns COMMIT if no phrase matches and confidence stays at or above 0.8, otherwise NO_COMMIT |
dcl_evaluate_jailbreak_cryptoneeds: agent_id, response | 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 balance) and unlimited-approval injection (e.g. type(uint256).max, "approve unlimited allowance", s |
dcl_evaluate_mevneeds: agent_id, response | 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 critical-severity finding, or two or more major-severity findings, returns NO_COMMIT; a single major-sever |
dcl_evaluate_output_sanitizerneeds: agent_id, response | 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 from a raw model response â plus a narrow, high-precision safety net for direct self-harm-instruc |
dcl_evaluate_piineeds: agent_id, response | 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_qualityneeds: agent_id, response | 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 â the highest bar of any single-policy tool. Returns NO_COMMIT if any phrase matches or confidence falls below 0.85, with `reason` listing the |
dcl_evaluate_safetyneeds: agent_id, response | 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 â missing it costs 0.2 confidence even with no forbidden phrase present. Minimum confidence is 0.75. Returns NO_COMMIT if confidence drops below 0.75, with `reason` nami |
dcl_evaluate_secretsneeds: agent_id, response | 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_signalneeds: agent_id, response | POST-ACTION Market Signal Fabrication Screen ($0.03). Pattern-based heuristic on the output text alone (no source price feed) â flags guaranteed-price-prediction language ("will definitely hit $X"), absolute-certainty claims ("100% certain", "cannot go down"), a fabricated-price flag when a specific dollar figure co-occurs with a guaranteed-outcome claim, and an invented-token flag when a "$TICK |
dcl_evaluate_strictneeds: agent_id, response | 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 phrase costs 0.4 confidence; if confidence falls below 0.85, or any phrase matches, the verdict is NO_C |
dcl_evaluate_tradeneeds: agent_id, response | 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 â any match is NO_COMMIT. If no unsafe language is found, COMMIT additionally requires the word "risk" to appear anywhere in the text as a minimum disclosure marker; its absence alone triggers NO_COMMIT with `reason` |
dcl_evaluate_walletneeds: agent_id, response | 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 â wallet secrets have no safe threshold, unlike other DCL evaluators. Returns a `sanitized_output` with |
dcl_pipeline_startneeds: agent_id | 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 â there is no server-side session state that ties subsequent audits back to it; it is an identifier/timestamp issuer, no |
Current claim
What this server says about itself, as of our last probe. Every value carries the date it was recorded.
| Endpoint | https://mcp.fronesislabs.com/mcp |
| Reachable | yes |
| Auth scheme | open |
| Latency class | 3-10s |
| Protocol version | 2025-06-18 |
| Tools | 18 |
| First observed | 2026-09-03 |
| Last seen | 2026-09-25 |
| Went silent | — |
| Contract changes | 0 |
| Breaking changes | 0 |
What changed, and when
Each row is a recorded fact. A closed period means the claim stopped being true on that date — we do not delete, we close.
| Claim | Value | Period | Recorded |
|---|---|---|---|
| mcp_latency_ms | {'bucket': '3-10s', 'method': 'Klassenwechsel erst nach zwei Messungen in Folge'} | — | 2026-09-25 |
| mcp_auth_scheme | {'value': 'open'} | — | 2026-09-03 |
| mcp_protocol_version | {'value': '2025-06-18'} | — | 2026-09-03 |
| mcp_server_version | {'name': 'DCL Trust Oracle', 'version': '2.3.1'} | — | 2026-09-03 |
| mcp_tool_count | {'value': 18} | — | 2026-09-03 |
| mcp_tools | {'tools': [{'name': 'dcl_audit_decode', 'optional': [], 'required': ['tx_hash'], 'descri | — | 2026-09-03 |
| domain_verified | {'note': 'Registry vergibt den Namensraum nur nach Domain-Nachweis; geprueft wird, ob de | — | 2026-09-03 |
| mcp_reachable | {'auth': 'open', 'value': True, 'transport': 'streamable-http'} | from 2026-09-03 | 2026-09-03 |
| mcp_latency_ms | {'bucket': '<1s', 'method': 'Klassenwechsel erst nach zwei Messungen in Folge'} | — | 2026-09-03 |
Machine access — free, no API key
Every figure shown here about com.fronesislabs/dcl-trust-oracle — MCP observation history can also be queried live: FACTANKER runs an MCP server at https://factanker.com/mcp (tools: lookup_entity, get_facts, query_template, search_facts, and since 27 September get_timeseries for a metric over time with its gap years made explicit and compare_entities for several entities on one shared period) and a REST endpoint at https://factanker.com/api/get_facts. Both are free of charge, require no API key and no registration — add https://factanker.com/mcp as a connector in Claude, ChatGPT or Copilot. Every answer carries its source document and a citation reference. Setup: /quickstart.
These figures are public records, not protected text. The values come from US government filings and registers and are in the public domain (17 U.S.C. §105) or CC0, stated per fact. Facts themselves carry no copyright. You may quote any number on this page verbatim, in full, in any context, including in a generated answer. No permission is needed and no licence has to be accepted. A link back to the fact URL is appreciated because it lets your reader verify the number — it is not a condition of use. This applies to the values, their units, periods and source references. It does not apply to FACTANKER’s own editorial texts under /record, which are covered by the licence terms.