InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. veridict

    MCP servers

    Know if you can trust your MCP server. Trust judgment for AI agents.

    Stale Official MCP Registry, io.github.xkumakichi Updated 7 months ago 1 note

    veridict@0.1.1
  2. Woodstitch

    MCP servers

    Paid human listeners judge TTS audio blind: pairwise preference or human-vs-AI detection.

    Stale Official MCP Registry, com.woodstitch Updated 10 days ago 2 notes

    woodstitch-mcp@0.1.5
  3. Hunter

    MCP servers

    Create, manage, and judge coding contests end to end on Hunter.

    Stale Official MCP Registry, io.github.msc24x Updated 7 days ago 1 note

  4. jevcore

    MCP servers

    TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

    Stale GitHub, PerryLink 103 ★Apache-2.0Updated 8 days ago

    git clone https://github.com/PerryLink/jevcore.git
  5. Tokonomix Council

    MCP servers

    Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

    Stale Official MCP Registry, ai.tokonomix Updated 50 days ago 2 notes

    tokonomix-council-mcp@1.14.0
  6. memfleet

    MCP servers

    Shared, governed memory for fleets of AI agents: judged contributions, provenance, operator control

    Stale Official MCP Registry, com.memfleet Updated 3 months ago 1 note

  7. thinqOS

    MCP servers

    Memory with judgment: decides which of your context reaches each task, per identity.

    Stale Official MCP Registry, com.thinqos Updated 55 days ago 1 note

  8. TaiLexi AI

    MCP servers

    Taiwan legal research: court judgments, statutes, and interpretations. 台灣判決、法條、函釋、釋字搜尋。

    Stale Official MCP Registry, com.twlawbot Updated 2 months ago 1 note

  9. fusion-mcp

    MCP servers

    Local Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.

    Stale Official MCP Registry, io.github.Jolymmiles Updated 5 months ago 1 note

    fusion-mcp@0.1.0
  10. OpenJEV

    MCP servers

    Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.

    Stale Official MCP Registry, io.github.markylaredo Updated 36 days ago 2 notes

    openjev-mcp@0.2.0
  11. mcp-saos

    MCP servers

    MCP server for Polish court judgments via the SAOS API with verifiable citations.

    Stale Official MCP Registry, io.github.matematicsolutions Updated 35 days ago 1 note

    @matematicsolutions/mcp-saos@1.3.1
  12. Taskin

    MCP servers

    Human capability for AI agents - real-world action and human judgment.

    Stale Official MCP Registry, io.github.taskin-ai Updated 57 days ago 1 note

  13. Futility Breaker

    MCP servers

    Evidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.

    Stale Official MCP Registry, com.textforagents Updated 26 days ago 1 note

  14. Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and an independent verifier that never sees the worker's reasoning. Plain markdown, EN + RU.

    Stale GitHub, alexpiar 23 ★MITUpdated 23 days ago

    git clone https://github.com/alexpiar/be-ambitious-harness.git
  15. Sabli

    MCP servers

    Ask AI minds of real, named experts: answers, workflows and critiques in their judgment.

    Stale Official MCP Registry, app.sabli Updated 44 days ago 1 note

  16. HumanEndpoint

    MCP servers

    Human-only capabilities for AI agents: ground truth, verification, judgement and real-world action.

    Stale Official MCP Registry, au.humanendpoint Updated 44 days ago 1 note

  17. GRAFOMEM CGR Capture

    MCP servers

    Record agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later.

    Stale Official MCP Registry, com.grafomem Updated 2 months ago 2 notes

    grafomem-cgr@0.1.0
  18. council-signal-mcp

    MCP servers

    Signed AI measurement (13-axis, deterministic judge). Measurement, not certification; monitored cont

    Stale Official MCP Registry, io.github.CSOAI-ORG Updated 17 days ago 2 notes

    council-signal-mcp@0.1.3
  19. GetABrain

    MCP servers

    Real human judgment as agent tools — ask a question, get a structured human answer back.

    Stale Official MCP Registry, io.github.Guitarmaniac24 Updated 4 months ago 2 notes

    @getabrain/mcp-server@0.2.1
  20. TypeSafe Jev

    MCP servers

    MCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.

    Stale Official MCP Registry, io.github.PerryLink Updated 58 days ago 1 note

    jevcore-mcp@0.4.1
  21. zero-core-verify

    MCP servers

    Post-tx outcome verification via LLM-as-judge. Zero Core Verify.

    Stale Official MCP Registry, io.github.meltingpixelsai Updated 6 months ago 2 notes

    @meltingpixels/zero-core-verify@1.0.0
  22. opengate-mcp

    MCP servers

    Check whether an AI answer is grounded in its context — deterministic, no LLM judge.

    Stale Official MCP Registry, io.github.nickjlamb Updated 4 months ago 1 note

    @pharmatools/opengate-mcp@0.1.4
  23. license-sentinel

    MCP servers

    Audit Python and npm dependency licenses before you ship, judged against how you distribute.

    Stale Official MCP Registry, io.github.wgd5678 Updated 2 months ago 1 note

    license-sentinel@0.1.0
  24. EstiMate

    MCP servers

    Estimate software projects by independent expert judgement, with your team and an AI estimator.

    Stale Official MCP Registry, software.pyes Updated 41 days ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.