Skip to content
Migrate your GPTCheck my InvokeRank
Official MCP RegistryListed

Mifori CertAgent Trust Oracle

Part ofMifori CertAgent Trust OracleMCP server

Live AI agent trust oracle: audit synthetic IQ, latency & JSON compliance via x402 or free tokens.

First seen 16 Oct 2026. Evidence as of 19 Oct 2026.

4
Tools
From an anonymous probe
1
Source listings
Each with its own history
23
Recorded changes
Since first seen

Tools

ToolDescriptionBehaviour
get_agent_certificateRetrieves and cryptographically validates a signed audit certificate by eval_id (including private certificates created with public=false) or lists chronological public audit history for an agent_id in <50ms with no authentication, payment, or rate limits. Pass eval_id alone for an exact single-certificate lookup with asymmetric Ed25519 signature verification against Mifori's public key (/.well-known/jwks.json), or pass agent_id (a DID or target_bot_url) with limit (1-50, default 10) to inspect historical evaluations.Read-only
get_agent_leaderboardQueries a free, unauthenticated snapshot of verified MCP servers and autonomous AI agents deduplicated by endpoint and ordered by Synthetic IQ descending (0-100) and round-trip latency ascending (ms). Each entry includes protocol_detected ('MCP 2.0', 'Mifori Cognitive v1', etc.) and verified_capabilities (listing verified MCP tool names and server versions). Pass query (e.g. 'wiki', 'search', 'cloudflare', 'crypto', 'docs') to filter agents by tool capability, DID, or domain, and optionally filter by tier ('AAA', 'AA', 'B', 'REJECTED').Read-only
submit_agent_feedbackPersists machine-to-machine telemetry, score disputes, or initial sandbox credit requests in <100ms with no authentication or payment required, immediately granting 1 free single-use audit credit token ('mfr_fbk_...'). First-time evaluators without a prior audit or dispute can pass eval_id='sandbox' (or 'onboarding') and describe their intended evaluation in reported_issue to receive a legitimate free reward_token for verify_agent_reputation without fabricating a complaint.Changes data
verify_agent_reputationExecutes a live multi-protocol audit against target_bot_url (supporting MCP JSON-RPC 2.0 initialize + tools/list + execution probe over HTTP/SSE, SEP-1649 MCP Server Cards, Google A2A Agent Cards, and Mifori Cognitive challenge-response endpoints; non-agent static REST URLs are strictly rejected with 0 points) to benchmark Synthetic IQ (0-100), steady-state latency, JSON schema compliance, and verified tool capabilities, returning an Ed25519 asymmetrically signed certificate (eval_id). Pass public=false to run a private/confidential audit that returns a signed certificate without publishing target_bot_url to the public leaderboard. Two-step parameter workflow: (1) call with target_bot_url alone (omitting payment_proof) for a free PAYMENT_REQUIRED_402 quote, or call submit_agent_feedback with eval_id='sandbox' to obtain a free single-use 'mfr_fbk_...' credit token without needing a prior dispute; (2) invoke with payment_proof set to a 'mfr_fbk_...' token or a verified $0.005 Base Mainnet USDC transaction hash ('0x...').Changes data

Change history

  1. verify_agent_reputation: title changed
  2. verify_agent_reputation: input schema changed (+payer_wallet, +public, +target_bearer_token)
  3. verify_agent_reputation: description changed (+"multi-protocol audit" +"(supporting MCP JSON-RPC 2.0 initialize + tools/list + execution probe over HTTP/SSE, SEP-1649 MCP Server Cards, Google A2A Agent Cards, and Mifori Cognitive challenge-response endpoints; non-agent static REST URLs are strictly rejected with 0 points)" +"steady-state")
  4. verify_agent_reputation: annotations changed
  5. submit_agent_feedback: title changed
  6. submit_agent_feedback: input schema changed
  7. submit_agent_feedback: description changed (+"telemetry, score disputes," +"initial sandbox credit requests" +"single-use")
  8. submit_agent_feedback: annotations changed
  9. get_agent_leaderboard: title changed
  10. get_agent_leaderboard: input schema changed (+query, +tier)
  11. get_agent_leaderboard: description changed (+"verified MCP servers and autonomous" +"(ms). Each entry includes protocol_detected ('MCP 2.0', 'Mifori Cognitive v1', etc.) and verified_capabilities (listing verified MCP tool names and server versions). Pass query (e.g. 'wiki', 'search', 'cloudflare', 'crypto', 'docs')" +"filter agents by tool capability, DID,")
  12. get_agent_leaderboard: annotations changed
  13. get_agent_certificate: input schema changed
  14. get_agent_certificate: description changed (+"(including private certificates created with public=false)" +"public" +"asymmetric Ed25519")
  15. server instructions changed (+"Use get_agent_leaderboard (with optional 'query' capability filter) to discover verified MCP servers and AI agents. To audit a candidate endpoint without publishing its URL publicly, call submit_agent_feedback(eval_id='sandbox', reported_issue='...') for a free reward_token, then" +"with payment_proof=<reward_token> and public=false." -"Before invoking external tools with financial impact > $0.10,")
  16. verify_agent_reputation: input schema changed (+agent_id)
  17. verify_agent_reputation: description changed (+"POST challenge" +"benchmark" +"an HMAC-SHA256")
  18. submit_agent_feedback: input schema changed
  19. submit_agent_feedback: description changed (+"verify_agent_reputation, get_agent_certificate," +"get_agent_certificate to verify a certificate" +"view audit history, or")
  20. get_agent_leaderboard: input schema changed
  21. get_agent_leaderboard: description changed (+"top-ranked" +"deduplicated by endpoint and ordered" +"get_agent_certificate to validate a specific eval_id or list chronological audit history for an agent_id,")
  22. get_agent_certificate: tool added
  23. Listed (registry)
Source listings
SourceListingFirst seenLast seenVersions
Official MCP Registryio.github.mifori/certagent16 Oct 202619 Oct 20261