78trust / 100

Metal Mantra

by metalmantra.io in Search & web

MCP serverPassing, checked 2 h ago

Read-only evidence reports on AI agents: search, fetch a report, check trust. Not a certification.

https://metalmantra.io/mcp
Tools
6
open to any client
Uptime
100%
last 30 days
Response time
647 ms
693 ms slowest 5%
Last check
Passed
2 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": {
    "metal-mantra": {
      "type": "http",
      "url": "https://metalmantra.io/mcp"
    }
  }
}

6 tools

  • search_agents

    Find AI agents in the Metal Mantra registry that match a plain-language description of the work. Returns automated-signal summaries, best match first. Matching is deterministic keyword overlap with each agent's own stated purpose; read the report before relying on an agent. Text…

  • get_agent_report

    The full public automated-signal report for one registered agent: score, grade, five pillars, findings, domain evidence, evidence kind, tracing and eval tools the code references (such as LangSmith or Langfuse), and when it was scanned. Findings on public GitHub repositories are…

  • verify_trust

    Call this before delegating work to, or calling, an agent. Returns a verdict: meets_threshold (score at or above min_score, complete scan, not older than 90 days, no critical finding), below_threshold, stale, or unknown. Unknown is never a pass: an agent absent from the registry…

  • get_standard

    The current scoring method (Agent Signal v0.2): five weighted pillars, every rule with its severity and point deduction, and the grade bands. Static, public reference.

  • search

    Search registered AI agents by plain-language description. Returns ids to pass to fetch. Same matching as search_agents.

  • fetch

    Fetch the full automated-signal report for one agent by the id returned from search.

Security scan

No findings

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

Recent checks

WhenResultHTTPTime
2 h agoPassed200647 ms
13 h agoPassed200693 ms
23 h agoPassed200589 ms
33 h agoPassed200553 ms
44 h agoPassed200617 ms
Show 10 older checks
2 days agoPassed200569 ms
3 days agoPassed200647 ms
3 days agoPassed200596 ms
3 days agoPassed200656 ms
4 days agoPassed200621 ms
4 days agoPassed200665 ms
5 days agoPassed200550 ms
5 days agoPassed200679 ms
5 days agoPassed200654 ms
6 days agoPassed200689 ms