MCP 및 연동

56 · 각 항목의 검토 근거를 확인하세요. 수록은 독립적인 실행 검증을 뜻하지 않습니다.

• typesafe-mcp

  itsmostafa · MCP 및 연동

  Claude Code, Claude Desktop, Codex, Pi에서 Jev에 질문하는 MCP 서버.

• jev-mcp

  jkudish · MCP 및 연동

  근거 확인, 콘텐츠 검사, 검색, 재정렬, 분류, 비교, 추출 등 8개 MCP 판단 도구를 제공한다.

• jev-mcp

  blakestone-x · MCP 및 연동

  Jev 분류·채점·예/아니요 판단·후보 매칭을 MCP 도구로 제공한다.

• Jevbridge

  gamesonrblx · MCP 및 연동

  ACP, MCP, CLI를 통해 Jev와 다른 모델을 공통 판단 인터페이스로 연결한다.

• pi-jev

  TheoOliveira · MCP 및 연동

  Pi Agent에 필요한 도구와 스킬을 찾고 구조화된 평가와 선택적 기록 필터링을 제공한다.

• jev-mcp

  rashedInt32 · MCP 및 연동

  분류, 점수, 참·거짓 판단과 일괄 질문을 제공하는 Jev MCP 서버 및 Claude Code 플러그인이다.

• jev-workbench

  molis-ai · MCP 및 연동

  로컬 화면에서 Jev 판단 함수를 정의, 시험, 게시하고 백엔드와 Agent에서 고정 버전을 호출한다.

• jev_ampcode

  thesammykins · MCP 및 연동

  제공된 선택지, 근거와 우선순위를 비교하는 Amp 플러그인이다.

• vellum-assistant

  vellum-ai · MCP 및 연동

  Vellum Assistant의 선택적 Jev provider가 대화 상태와 명시적 질문을 TypeSafe에 보낸다.

• synkora-ai

  getsynkora · MCP 및 연동

  Synkora는 분류, 점수와 참·거짓 판단을 위한 선택형 TypeSafe 도구를 제공한다.

• jevwire

  Brainwires · MCP 및 연동

  Agent용 Jev MCP 도구·내장 라이브러리·Claude Code hooks를 제공한다.

• jev-mcp

  BYK · MCP 및 연동

  개별 질문, 일괄 처리, 질문·임계값 비교를 제공하는 평가 중심 Jev MCP 서버다.

• jev-classifier

  felpsdev · MCP 및 연동

  코딩 Agent용 로컬 Jev 도구 라우터로 MCP 제안 인터페이스도 제공한다.

• plasmallm

  joshuaeroman · MCP 및 연동

  KDE Plasma 어시스턴트 위젯에서 구조화된 판단을 보여주는 Jev Decisions 어댑터.

• tenbin

  simota · MCP 및 연동

  질문 lint·배치 평가·보정으로 Jev 판단을 설계하는 문서·MCP server·Skill.

• openclaw-typesafe-ai

  Olli0103 · MCP 및 연동

  명시적으로 호출하는 typesafe_decide 도구 하나를 등록하는 독립 OpenClaw 플러그인.

• pi-typesafe

  DevMortimer · MCP 및 연동

  판단 도구·터미널 실험 명령·다른 확장용 API를 제공하는 Pi Jev 확장.

• n8n-nodes-typesafe-jev

  n3ndor · MCP 및 연동

  TypeSafe Jev에 구조화된 질문을 보내는 n8n 커뮤니티 노드.

• openrouter-jev-mcp

  ctmx · MCP 및 연동

  A Python decision gateway and Model Context Protocol (MCP) server exposing TypeSafe's Jev model through OpenRouter's decisions endpoint to Claude Code, Codex, and Cursor agents.

• jev-mcp

  rajasekharponakala · MCP 및 연동

  MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents

• jev-rust-review

  kindintelligence · MCP 및 연동

  Rust-aware code review for Claude Code and coding agents, powered by TypeSafe Jev

• mcp-server-jev

  MattiooFR · MCP 및 연동

  Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.

• jev-codex-plugin

  integrate-your-mind · MCP 및 연동

  Open-source Codex plugin for TypeSafe Jev decision consultation, failure diagnosis, and evidence-based completion review

• jev-mcp

  CodeIA-Academy · MCP 및 연동

  MCP local que expone Jev (TypeSafe) como herramienta para Claude Code, Codex, Hermes y cualquier agente: ask_jev y list_jev_models, sin dependencias

• jev-eyes

  LeddoEngano · MCP 및 연동

  Also in the state: `image` (size, source), `blocks` (`[x, y, w, h]` boxes with OCR confidence) and, if installed, `labels`. `see(img, compact=True)` keeps only `image`, `text` and top label names when tokens matter more than positions.

• jev-agent-toolkit

  reiswaffel78 · MCP 및 연동

  Jev-first portable Agent Skill and optional MCP bridge for Claude Code, Codex, Cursor and compatible agents.

• jev-mcp

  Songokou1983 · MCP 및 연동

  Local MCP server exposing TypeSafe Jev (System One decision model) as native Claude Code / Codex tools

• jev-mcp-spring

  Ashfaqbs · MCP 및 연동

  On success each tool returns its typed result directly. On failure the tool call fails at the MCP protocol level (`isError: true`) with a short, safe message — no response body or stack trace is ever echoed back.

• typesafe-jev-mcp

  anasbekheit · MCP 및 연동

  This repository is an MCP server for TypeSafe Jev that provides a single evaluate tool taking state plus typed questions and returning noul, choice, or score answers with probabilities.

• jev-mcp-server

  wangkuangkuang · MCP 및 연동

  MCP server for Jev (TypeSafe System One): the three official question types — choice, score, noul — plus batch classify. Calibrated probabilities, ~0.5s, <$0.001/call.

• jev-as-quant

  jiayylu · MCP 및 연동

  Typed System-1 decisions (Laya/Jev) as the judgment layer of a quant research stack, with Claude as System 2. Requirements → design → code → experiments.

• jev-skill-router

  himomohi · MCP 및 연동

  Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.

• typesafe-jev-opencode

  moisesfilho · MCP 및 연동

  Jev is not a conversational replacement for Gemini, Claude, or GPT. It evaluates application state against typed questions and returns structured answers and probabilities that an agent can use to route or gate work.

• jev-in-mcp

  chy4pro · MCP 및 연동

  MCP relay that adds use_jev to every server: Jev picks the tool calls, the calling model writes the values Jev cannot choose, the relay executes. Built on jev-dev-kit.

• jev-agent-kit

  walidboulanouar · MCP 및 연동

  jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.

• jev-screen-mcp

  jiawei686 · MCP 및 연동

  Single-purpose MCP server (one tool, one job): a content-moderation gate powered by TypeSafe Jev (System One decision model).

• jev-review-mcp

  jiawei686 · MCP 및 연동

  Single-purpose MCP server (one tool, one job): a code-review gate powered by TypeSafe Jev (System One decision model).

• jev-mcp

  ieee0824 · MCP 및 연동

  A Rust MCP server for TypeSafe AI Jev structured decisions

• jev-toolkit

  jbt95 · MCP 및 연동

  MCP-first toolkit for TypeSafe/Jev — the System One decision model. One stdio server (jev mcp) serves any MCP-capable harness, backed by one local event log and Prometheus impact metrics you can scrape into your own Grafana.

• n8n-nodes-jev

  rahulthakore16 · MCP 및 연동

  Jev by TypeSafe AI for n8n: typed decisions, probabilities, and confidence-aware workflows

• jev-judge-mcp

  PyModel · MCP 및 연동

  Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.

• jev-mcp-open-source

  baize7815 · MCP 및 연동

  Self-hosted Jev MCP on Cloudflare Workers with intent routing, retrieval reranking and batch judgments

• jev-mcp

  codaaiteam · MCP 및 연동

  MCP server for Jev (TypeSafe AI's System One model) — give any agent typed, calibrated decisions: classify, score, check, gate risky tool calls. Try free: jevtypesafeai.com

• jev-playwright-mcp

  krw82 · MCP 및 연동

  Jev-augmented Playwright MCP proxy — page-state triage, prompt-injection shielding, goal-based snapshot pruning, risky-action gating. Drop-in wrapper around @playwright/mcp for any coding agent.

• jev-tool-search

  kachar · MCP 및 연동

  Tool search for LLM agents: BM25 vs embeddings vs rerankers vs Jev on 525 real MCP tools, plus an experimental Jev search engine

• Jev-AI-Skill

  King4s · MCP 및 연동

  One AI skill + MCP server for Claude Code, Codex and Hermes: Jev (TypeSafe) gates large-model turns (event triage, review verdicts, owner questions, tool choice), runs build-and-repair loops with independent review, routes models and skills, and guards Git steps. Script-only watch mode and a shared HTTP server.

• toolJev

  VishiATChoudhary · MCP 및 연동

  Code Mode for MCP, where the sub-model is a calibrated decision model (Jev), not an LLM. Benchmarked on MCPToolBench++, LiveMCPBench, When2Call and live Claude agents.

• jevmod

  ohernandezdev · MCP 및 연동

  Moderation for communities and apps: every message gets a probability for **spam, scam, harassment, nsfw, off-topic, self-harm, doxxing, sexual content involving minors**, and for **rules you write in plain English**. You set the thresholds and the actions. Every decision is logged with its numbers.

• jev-mcp

  Afloat16 · MCP 및 연동

  `jev-mcp` exposes TypeSafe AI's Jev decision model as four conservative, read-only MCP tools for **bounded probabilistic decisions**.

• harness-router

  Protocol-Lattice · MCP 및 연동

  Fast decision routing for agent harnesses — native MCP with Jev for tool selection and MCTS for multi-step decisions.

• JevTrace

  123wwwa · MCP 및 연동

  An MCP server that cuts coding-agent token usage by retrieving only the relevant JS/TS code using the TypeScript compiler and Jev.

• JevScout

  yctimlin · MCP 및 연동

  Jev decides what reaches your coding agent: verbatim, recoverable context for Claude Code and reviewed operations for Codex. npm i -g jevscout

• jev-mcp

  legostin · MCP 및 연동

  MCP server that lets Claude Code, Codex & AI agents drive a real Chrome browser with JEV (TypeSafe System One): ~100 ms typed decisions, calibrated confidence, human-in-the-loop questions, safety gates and a debug trace.

• android-jev

  FZ2000 · MCP 및 연동

  Whichever way it reaches the server, the key never appears in a state, a log, a run folder or a transcript.

• jev-netlify-mcp

  demircigoksu · MCP 및 연동

  Free, key-locked TypeSafe Jev via Netlify AI Gateway, plus an MCP server for Claude Code, Codex and Claude Desktop

• mcp-router

  Amantux · MCP 및 연동

  Jev System One 기반 오픈소스 MCP 라우터로, 수많은 도구 중 작업에 필요한 하위 집합을 단일 패스 판정으로 동적 라우팅합니다.