Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
veridict
MCP serversKnow if you can trust your MCP server. Trust judgment for AI agents.
veridict@0.1.1 -
Woodstitch
MCP serversPaid human listeners judge TTS audio blind: pairwise preference or human-vs-AI detection.
woodstitch-mcp@0.1.5 -
Hunter
MCP serversCreate, manage, and judge coding contests end to end on Hunter.
-
jevcore
MCP serversTypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.
git clone https://github.com/PerryLink/jevcore.git -
Tokonomix Council
MCP serversMulti-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
tokonomix-council-mcp@1.14.0 -
memfleet
MCP serversShared, governed memory for fleets of AI agents: judged contributions, provenance, operator control
-
thinqOS
MCP serversMemory with judgment: decides which of your context reaches each task, per identity.
-
TaiLexi AI
MCP serversTaiwan legal research: court judgments, statutes, and interpretations. 台灣判決、法條、函釋、釋字搜尋。
-
fusion-mcp
MCP serversLocal Fusion MCP: panel->judge->synthesis on the Claude CLI subscription, no OpenRouter.
fusion-mcp@0.1.0 -
OpenJEV
MCP serversTyped AI judgments for agents: choice, score, and yes/no probabilities instead of prose.
openjev-mcp@0.2.0 -
mcp-saos
MCP serversMCP server for Polish court judgments via the SAOS API with verifiable citations.
@matematicsolutions/mcp-saos@1.3.1 -
Taskin
MCP serversHuman capability for AI agents - real-world action and human judgment.
-
Futility Breaker
MCP serversEvidence-bound stopping for agents: judgment ledger, binding futility verdicts, signed receipts.
-
be-ambitious-harness
SkillsMake 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.
git clone https://github.com/alexpiar/be-ambitious-harness.git -
Sabli
MCP serversAsk AI minds of real, named experts: answers, workflows and critiques in their judgment.
-
HumanEndpoint
MCP serversHuman-only capabilities for AI agents: ground truth, verification, judgement and real-world action.
-
GRAFOMEM CGR Capture
MCP serversRecord agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later.
grafomem-cgr@0.1.0 -
council-signal-mcp
MCP serversSigned AI measurement (13-axis, deterministic judge). Measurement, not certification; monitored cont
council-signal-mcp@0.1.3 -
GetABrain
MCP serversReal human judgment as agent tools — ask a question, get a structured human answer back.
@getabrain/mcp-server@0.2.1 -
TypeSafe Jev
MCP serversMCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.
jevcore-mcp@0.4.1 -
zero-core-verify
MCP serversPost-tx outcome verification via LLM-as-judge. Zero Core Verify.
@meltingpixels/zero-core-verify@1.0.0 -
opengate-mcp
MCP serversCheck whether an AI answer is grounded in its context — deterministic, no LLM judge.
@pharmatools/opengate-mcp@0.1.4 -
license-sentinel
MCP serversAudit Python and npm dependency licenses before you ship, judged against how you distribute.
license-sentinel@0.1.0 -
EstiMate
MCP serversEstimate software projects by independent expert judgement, with your team and an AI estimator.
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.