DCL Trust Oracle
Related Servers
Alternatives to DCL Trust Oracle
No user-submitted related servers found.
Related Servers
- AlicenseBqualityAmaintenanceA governance proxy for AI tools — every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.13MIT
- AlicenseNot gradedqualityAmaintenanceGates every AI agent tool call against your policy before it runs, then writes a hash-chained, tamper-evident record of what was decided and what happened. Anyone can verify that record offline, without your software, your systems or any key you hold.12AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceCryptographic proof of every AI decision. An immutable, verifiable audit trail MCP server.1MIT
- FlicenseNot gradedqualityDmaintenanceOn-chain trust verification for AI agent tools. Agents query skill attestations, audit levels, and risk scores before running third-party MCP servers, so you know what's safe before you execute.1-
- AlicenseAqualityBmaintenanceAI agent provenance, trust, and auditability layer. VERITAS multi-gate scoring, Cortex approval gates, S.E.A.L. hash-chain audit ledger, and semantic RAG with cryptographic provenance tracking for every decision an agent makes.275MIT
- AlicenseNot gradedqualityCmaintenanceMCP server providing immutable audit logging, policy enforcement, and compliance reporting for AI agent workflows, enabling regulatory compliance and chain integrity verification.MIT
TDQS
Scored across 18 tools
Most tools have clearly distinct purposes, with detailed descriptions differentiating the many evaluate_* policies. However, the overlap between fast/strict and jailbreak/jailbreak_crypto could cause misselection without careful reading.
The dcl_ prefix and snake_case are consistent, and the verb-object pattern (evaluate_*, audit_*, commit) is mostly followed. Deviations include dcl_evaluate_output_sanitizer, which is a misnomer (it sanitizes, not evaluates), and dcl_pipeline_start, which doesn't follow the clean verb-object pattern.
At 18 tools, the set is larger than typical, but the server's broad scope (pre-action checks, post-action scans, crypto-specific screens, commit/receipts) justifies the count. It feels slightly heavy but not excessive.
The surface covers the full audit lifecycle: pre-action evaluation, post-action scanning, sanitization, commit, and audit retrieval. The main gap is dcl_pipeline_start, which is explicitly a stub with no server-side session linking, and there's no standalone chain-integrity verification tool (only mentioned within deep audit).