Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
jev-use
MCP serversTyped yes/no, pick-one and score judgments from Jev in one batched call; typed escalation back.
jev-use@0.8.0 -
jevway
MCP serversHand a browser goal to TypeSafe Jev in your Chrome or a throwaway one; get one checked summary.
jevway@0.5.3 -
jev-guide
MCP serversSet up the JEV model router for Claude Code, Codex and Cursor, and install MCP servers.
-
Cover Signal — Jevan NFL Picks
MCP serversFree NFL ATS, moneyline and over/under picks, separate track records, and Jevan AI methodology.
-
JevLint-LE
MCP serversLint questions for TypeSafe's Jev and OpenAI's Luna offline, or ask the model itself with your key.
jevlint-le-mcp@0.8.1 -
DecisionLint: Jev/Luna Lint
MCP serversLint Jev and Luna decision-model questions, or ask the model to check them with your key.
decisionlint-mcp@1.1.1 -
Politicians by Jev
MCP serversAsk anything about 100 famous US politicians; Jev, TypeSafe AI's model, scores all 100 and picks.
-
Ask Jev
MCP serversEvaluate state with typed choice, score, and probability questions.
-
zerikai_memory
MCP serversA standalone local-only Python MCP server that gives any IDE persistent, workspace-isolated memory. works with any IDE supporting MCP servers
git clone https://github.com/KikeVen/zerikai_memory.git -
Jev Filter
MCP serversRead-only semantic filtering, code search, log triage and traceable evidence for AI agents.
@apixly/jev-filter@0.4.2 -
jevjam
MCP serversTyped decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU
ghcr.io/beremaran/jevjam:0.3.3 -
browserpaw
MCP serversBrowserClaw - Control your everyday Chrome browser from AI agents, without losing logins or focus
git clone https://github.com/GoldenLoaf24h/browserpaw.git -
jev-ultrafast-mcp
MCP serversHand browser work off to a server-side agent: read the page as a table, act, then verify.
jev-ultrafast-mcp@0.1.5 -
Jagent
MCP serversGrade essays, check resumes, and ask typed yes/no, choice and rubric questions, powered by Jev.
-
nudge
MCP serversA typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.
git clone https://github.com/NekomyaDev/nudge.git -
Arbitype
MCP serversTyped decision tools for AI agents, powered by TypeSafe Jev.
arbitype@0.7.0 -
agentgrasp
MCP serversYes/no questions about local files, and relevant-file search, with TypeSafe Jev
agentgrasp@0.1.0 -
judgevet
MCP serversAsk TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.
judgevet@0.23.0 -
Stats Explorer
MCP serversVerified statistics for AI agents: guided tests, A/B tests, Tukey HSD, reports, optional Jev checks.
stats-explorer-mcp@1.5.1 -
TypeSafe MCP
MCP serversHost-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.
typesafe-mcp@0.5.2 -
AgentIndex x402
MCP serversJev-powered decisions, web search, PDF/web to Markdown, summarize. From $0.001, no API key.
-
SCRIPTMASTERLABS — Cascade Graph
MCP serversCascade Graph MCP: macro decision capsules + Jev jury review over a hash-chained calibration log.
-
SCRIPTMASTERLABS — Verdict Protocol
MCP serversVerdict Protocol MCP: five-juror Jev decisions. Seal settle-proven 2026-11-02 (SELF-PROOF).
-
TypeSafe
MCP serversGet calibrated yes or no answers, choices and scores from TypeSafe's Jev, for one item or 1000 rows.
@foreverworks/mcp-typesafe@0.1.3
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.