Skip to main content
Glama
fairquery

fairquery-agent-trust-mcp

Official
by fairquery
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to fairquery-agent-trust-mcp

No user-submitted related servers found.

    Related Servers

    • SCML MCP Server

      ravindu57
      F
      license
      Not graded
      quality
      C
      maintenance
      Enables LLM agents to enforce security policies by authorizing tool calls, scanning for prompt injection, checking memory writes, redacting PII, and accessing audit trails through MCP.
      -

    • Scml

      ravindu57
      A
      license
      Not graded
      quality
      B
      maintenance
      Security middleware for LLM agents. Authorize tool calls, scan for injection, quarantine poisoned memory, and redact PII — all through MCP. 0% injection success rate on 1,054 tested attacks.
      Apache 2.0

    • vibecheck

      ArisRhiannon
      A
      license
      A
      quality
      D
      maintenance
      Agent-native "safe to ship?" security gate for AI-generated code. Uses real parsers and inter-rocedural taint analysis (JS/TS, Python, Go) to flag the classes AI coding agents get wrong — secrets, SQL injection, SS, SSRF, path traversal, command injection, weak JWT/CORS — and ranks findings by confidence. Exposes a scan tool over MCP.
      1
      8 npm
      2
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4.5/5.0

    Scored across 12 tools

    Disambiguation4/5

    Within each domain the tools are clearly separated by action (scan vs redact vs guard) and by free-local vs paid-Actor tiering, and every description includes explicit WHEN NOT cross-references. The only residual overlap is the deliberate free/paid pairing (pii_scan_text vs pii_guard_documents, email_check_syntax vs email_validate_deliverability, osv_query_packages vs osv_audit_dependencies) plus the convenience wrapper trust_screen_lead, but each is clearly bounded by scope and cost.

    Naming Consistency5/5

    All 12 tools use consistent snake_case with a domain prefix followed by a verb/action phrase (pii_*, email_*, sanctions_*, osv_*, trust_*). The pattern is predictable and readable throughout, with no mixing of conventions.

    Tool Count5/5

    Twelve tools are well-scoped across four coherent domains (PII, email, sanctions, OSV), each with roughly three complementary operations plus a combined orchestration tool. No tool feels redundant; every one earns its place.

    Completeness4/5

    Each domain covers discovery/catalog, free local, and paid hosted operations, and the combined trust_screen_lead provides an end-to-end workflow, so there are no dead ends. Gaps are acknowledged rather than hidden (no PEP/adverse media, no SMTP probing, no image OCR), which are minor for the stated purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources