stealthstack.ai Status Publish a catalog

Agent trust and governance

Resources for controlling what agents can do and proving what they did.

They cover agent identity and keys, signed receipts and provenance, reputation and ratings, guardrails and approval steps, audit logs and AI governance.

Listings are what publishers declare in their ARD catalogs and the registries StealthStack reads. The category and summaries are our reading of each listing. Each listing links to its own page with the publisher's endpoint.

All types MCP serversSkillsA2A agentsAPIs
Identity and DIDsProvenance and receiptsReputation and ratingsGuardrails and policyAudit loggingAI governance
  1. APIVouchSpec Paid Exact-Commit Validation API Buys static validation and signed evidence for one agent skill commit; 0.25 USDC.
  2. A2A AGENTMolTrust Trust Registry Trust registry for agents: DIDs, verifiable credentials and trust scores on Base.
  3. A2A AGENTOverwing Checks text before an agent sends it and identifies AI crawlers from User-Agents.
  4. MCP SERVERLemma MCP Server Registers documents and queries ZK proofs to verify attributes without plaintext.
  5. APIDynamic Feed Witness: signed receipts for machine-to-machine transactions Third-party witness that issues signed, timestamped receipts for agent transactions.
  6. A2A AGENTValidate Agent Guardrails: prompt-injection screening, PII redaction, validation; 200 free then x402.
  7. SKILLagent-governance Skill with patterns for adding governance, safety and trust controls to AI agents.
  8. SKILLverify-agent-action Skill reviewing proposed agent actions and approval packets before execution.
  9. SKILLEntra Agent Id Skill for creating OAuth2-capable agent identities with Microsoft Entra Agent ID.
  10. A2A AGENTDecision Anchor — A2A Agent A2A agent recording content-blind accountability boundaries for agent actions.
  11. MCP SERVERFLINT Verification MCP Server Pre-transaction fraud checks, agent passports, authority verification.
  12. A2A AGENTVouchSpec Agent Skill Evidence A2A discovery for x402-paid validation and signed evidence of a GitHub agent skill commit.
  13. A2A AGENTLEGIT Trust scores for x402 merchant addresses across 20 chains; verdicts paid in USDC.
  14. MCP SERVERSpoolis acceptance MCP server Verifies delivered work against criteria and issues signed receipts; x402.
  15. A2A AGENTAccord Trace Tamper-evident evidence receipts and verification for agent actions.
  16. SKILLExecution contract Free behavioral contract skill: success criteria, bounded retries, evidence ledger.
  17. APIDecision Anchor — Core API (OpenAPI) REST API for recording agent decision declarations and execution envelopes.
  18. A2A AGENTAverray — trusted agent work + identity runtime Outcome-assurance on Polkadot: verify work, release payment, signed receipts.
  19. SKILLgoogle-cloud-solution-multi-agent-security Skill for designing and securing Google Cloud Agent Gateway multi-agent traffic.
  20. A2A AGENTGAIP Trust & Assurance Agent Verifies GAIP receipts and compiles evidence packs and incident bundles.
  21. A2A AGENTVaultfire Agent Hub On-chain agent identity, reputation, bonds and escrow across 4 chains.
  22. MCP SERVERGAIP MCP server (five tools; full catalogue at /mcp/all) Four read-only tools to check, watch, diagnose and verify AI agents and MCP servers; free.
  23. MCP SERVERGAIP Trust & Assurance Agent (MCP) MCP card: verifies GAIP receipts and compiles evidence packs and incident bundles.
  24. SKILLDd Audit Ai Activity Datadog skill auditing Bits AI assistant tool calls and resources accessed.
  25. APISpoolis acceptance API API for acceptance runs: criteria, judges, verdicts, signed receipts.
  26. A2A AGENTCouncil of AI Measurement Agent AI-governance measurement agent publishing a signed governance and safety board.
  27. SKILLnemoclaw-user-manage-policy Skill editing allowed endpoints and egress rules in NemoClaw sandbox policy.
  28. SKILLSkill Scanner Skill to scan agent skills for security issues.
  29. SKILLentra-agent-user Skill that creates Entra Agent Users so agents act with user identities.
  30. SKILLnemoclaw-user-configure-security Skill presenting a risk framework for NemoClaw sandbox security controls.
  31. A2A AGENTAgent Guild A2A Agent A2A access to evidence-based agent vetting and Agent Guild utilities.
  32. SKILLAgent Guild Skill Skill for vetting agent counterparties, verifying reputation and settling work.
  33. A2A AGENTAgent Readiness Checker Tests whether a requesting agent would hire an A2A agent; six pass/fail findings.
  34. MCP SERVERFocxle deal rooms: AI governance for B2B deals between agents Deal rooms where businesses' agents negotiate under owner rules with a tamper-evident log.
  35. APIDecision Log REST API REST facade over the Decision Log GraphQL schema for decision search and provenance.
  36. APIFLINT Verification API Verifies agent authority at transaction time with signed records.
  37. SKILLnemotron-policy-generator Skill generating custom safety policies for Nemotron content-safety guardrails.
  38. MCP SERVERDecision Log MCP Server Authenticated access to an immutable decision log with provenance and audit history.
  39. MCP SERVERProofRail MCP Release Certifier MCP release checks for required tools and schema drift with receipts; free preflight.
  40. MCP SERVERGAIP Witness Agent (MCP) MCP card: records delivery checks, witnesses results and checks cited quotes.
  41. MCP SERVERGAIP Buyer Assurance Agent (MCP) MCP card: records a buyer's service request and checks what was delivered.

Related categories

AI models and MLOpsAgent memory and contextAgent orchestrationAgent discoveryAgent payments All categories