78trust / 100

Mifori CertAgent Trust Oracle

by agent.mifori.com in Security & trust

MCP serverPassing, checked 1 h ago

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

https://agent.mifori.com/mcp?v=1
Tools
4
open to any client
Uptime
100%
last 30 days
Response time
365 ms
3.5 s slowest 5%
Last check
Passed
1 h ago, next in 4 h

Scan it nowHow to connect

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to connect

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "mifori-certagent-trust-oracle-2": {
      "type": "http",
      "url": "https://agent.mifori.com/mcp?v=1"
    }
  }
}

4 tools

  • verify_agent_reputation

    Executes 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…

  • submit_agent_feedback

    Persists 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…

  • get_agent_leaderboard

    Queries 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.)…

  • get_agent_certificate

    Retrieves 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…

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
1 h agoPassed200429 ms
13 h agoPassed200285 ms
24 h agoPassed2003.5 s
38 h agoPassed200444 ms
2 days agoPassed200338 ms
Show 10 older checks
3 days agoPassed200374 ms
3 days agoPassed200416 ms
4 days agoPassed200523 ms
5 days agoPassed2003.5 s
5 days agoPassed200355 ms
6 days agoPassed200348 ms
6 days agoPassed200342 ms
7 days agoPassed2003.1 s
7 days agoPassed2003.5 s
8 days agoPassed200321 ms