Skip to main content
Glama
Sign In
fairquery-agent-trust-mcp

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
      5 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

    A4.8/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool occupies a clearly distinct slot: free-local vs paid-hosted PII handling, detect vs redact vs restore, syntax-only vs MX email checks, manifest audit vs exact-version query vs advisory lookup. The few apparent overlaps (pii_guard_documents restore mode vs pii_restore_text, trust_screen_lead vs its two component tools) are explicitly called out in WHEN/WHEN NOT sections with guidance on which to pick. An agent should have no trouble selecting the right tool.

    Naming Consistency5/5

    All 13 names are snake_case with a stable domain_prefix_verb_noun pattern (pii_*, email_*, sanctions_*, osv_*, trust_screen_lead). The domain prefixes make grouping obvious and the verb choice (scan/redact/restore/list/guard/check/validate/screen/query/get/audit) is used meaningfully and consistently.

    Tool Count5/5

    13 tools is a well-scoped size for a multi-domain trust server covering PII, email, sanctions, and dependency vulnerabilities, with roughly 3-5 tools per sub-domain. Every tool has a distinct role (a free local variant, a paid hosted variant, a catalogue, or a merged convenience call) rather than being filler.

    Completeness4/5

    The surface covers the full lifecycle in each area: PII detect/redact/restore/guard plus a detector catalogue, email syntax + deliverability, sanctions screening + source listing, and OSV query/get/audit, with trust_screen_lead tying email and sanctions together. Minor gaps remain, such as no way to check APIFY_TOKEN credit/payment status before invoking paid tools (only error codes) and no image OCR, but these are stated limitations agents can work around.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Resources