MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Jev agent workstation.
★ 1 -
A Rust MCP server for TypeSafe AI Jev structured decisions
MIT ★ 1 -
Runs the jev-browser-use click loop in Google Chrome for any MCP client.
MIT ★ 1 -
Local MCP server for TypeSafe Jev typed decisions, with Codex integration
npm MIT ★ 1 -
Jev MCP Serverno update data
MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
pypi -
MCP server for searching and reading the official TypeSafe Jev documentation
npm MIT -
MCP server (stdio) exposing TypeSafe's Jev (System One) decision model as tools.
npm Apache-2.0 -
MCP server exposing TypeSafe's Jev model as a typed evaluate tool.
cargo MIT ★ 3 -
MCP server exposing TypeSafe Jev as typed, calibrated decision tools for coding agents
npm MIT -
MCP server for TypeSafe Jev — System One Model. Two tools: jev_decide (noul/choice/score) and jev_list_models.
npm MIT -
MCP server that gives an agent typed, calibrated judgments from TypeSafe's Jev model
npm MIT -
MCP server exposing TypeSafe Jev (System One decision model) through the OpenCode inference endpoint
npm MIT -
Brave Search MCP server with intent-aware Jev content filtering.
npm MIT -
MCP server for Jev AI (jev-ai.pro): classification, scoring, yes/no checks, action assessment, batched decisions and saved judges.
MIT -
MCP server for typed decisions with Jev / System One via OpenRouter or TypeSafe
go Apache-2.0 ★ 3 -
mcp-server-jevactive
MCP server for Jev, TypeSafe's System One model: typed choice, score, and noul questions over MCP
npm MIT -
MCP server exposing one tool: ask Jev a typed question and get a short answer back.
MIT -
MCP local que expone Jev (TypeSafe) como herramienta para Claude Code, Codex, Hermes y cualquier agente: ask_jev y list_jev_models, sin dependencias
MIT ★ 3 -
Community experimental MCP server and Pi adapter for bounded TypeSafe Jev judgments
MIT -
将你的jev变成mcp插件,接入任意agent(Claude,codex,Cherry Studio)。辅助llm决策层。Turns your jev into an MCP plugin, helping LLM make decisions.
MIT -
Minimal MCP server exposing TypeSafe's Jev System One model as a single narrow evaluation tool.
npm MIT -
Serveur MCP pour piloter Firefox avec Claude : Jev (TypeSafe) choisit les clics, Claude planifie. Benchmark inclus.
MIT ★ 1 -
Free, key-locked TypeSafe Jev via Netlify AI Gateway, plus an MCP server for Claude Code, Codex and Claude Desktop
MIT ★ 2 -
jev-mcp-serveractive
MCP server for TypeSafe Jev — structured semantic judgment (yes/no, pick-one, graded score) with calibrated probabilities
npm MIT -
MCP server wrapping TypeSafe's Jev System One models — typed noul/choice/score judgments for AI agents
AGPL-3.0 ★ 2 -
High-speed System One Jev AI decision gateway and MCP server powered by OpenRouter
MIT ★ 3 -
jev-kol-mcpactive
MCP server for micro-KOL discovery, Jev fit scoring, and outreach drafts
npm MIT -
Typed AI decisions for Codex, Claude and any MCP client, powered by TypeSafe Jev. Classify, score and evaluate with one generic tool.
MIT ★ 2 -
MCP server for decision models with TypeSafe Jev, Cloudflare Clef, OpenRouter, and local providers.
MIT -
A guarded MCP layer for Jev-powered browser decisions with isolated Playwright execution and explicit human approval.
MIT -
TypeScript MCP server that finds TikTok and YouTube micro-KOLs, tags their niche, scores campaign fit with Jev, and drafts outreach emails. Results are cached locally in SQLite.
MIT ★ 1 -
MCP server that routes a question to the best tool using a Jev decision engine (/v1/systemone). Works with any Jev-compatible server — Laya is one.
npm MIT -
MCP server that lets Claude Code and Claude Desktop drive the jev-ultrafast browser agent in your real Chrome, with a domain-bound safeguard
MIT -
Eval-first MCP server for TypeSafe's Jev: prototype typed questions, map them over many items, and measure them against labeled fixtures.
npm MIT -
MCP server that gives coding agents a judge: twelve jev_* tools for typed decisions and probabilities, plus a tray app and a Claude Desktop bundle.
MIT ★ 1 -
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.
MIT ★ 3 -
Run the Jev MCP server inside DeepSeek Harness. Typed judgment tools (verify, screen, find, review, gate, and the rest) register as mcp__jev__*. Provider keys stay in DSH credentials. Jev is not a chat model.
npm MIT -
Review public code and documents with Jev in Codex and Claude Code: ranking, batch screening, claim checks, spend limits, and evaluation tools.
Apache-2.0 -
Browser automation MCP server whose decisions are made by Jev (TypeSafe System One) typed decisions instead of an LLM reading the DOM.
npm MIT -
MCP server exposing TypeSafe's Jev as a `judge` tool for typed judgments with calibrated probabilities. Works in any MCP client; ships an optional Claude Code plugin wrapper.
npm MIT -
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
npm MIT ★ 7 -
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
MIT ★ 3 -
MCP server that runs plain-language browser steps. Jev, a typed decision model, picks the control on each page instead of an LLM reading the DOM.
npm MIT -
Delegate browser operations to an ultra-fast MCP server, executing full page tasks in seconds with one tool call.
MIT -
TypeSafe AI Jev MCP server for bounded probabilistic decisions: four read-only stdio tools for choices, routing, risk signals, and yes/no gates. Conservative second opinions with installers for Codex, Claude Code, Cursor, Kimi, Gemini CLI, and other MCP clients.
MIT ★ 1 -
MCP search server for a self-hosted SearXNG, with BM25F ranking and optional decision-model reranking
MIT -
MCP server exposing TypeSafe Jev as purpose-built judgment tools: verify claims, screen for injection, find, rerank, classify, decide, compare passages, extract fields, review patches, and gate completion claims, each with typed probabilities.
npm MIT -
MCP server that returns calibrated probabilities for an agent's own decisions, with an act/escalate gate, across local Laya and remote Jev engines.
NOASSERTION -
Jev - intelligent AI router and supervisor: classifies coding tasks, picks the best-fit model (Claude/Codex/Gemini/DeepSeek), and supervises tool calls through a Tool Gate. Runs as a Zed ACP external agent (jev-acp) or as an MCP server any MCP-compatible
npm MIT -
3+1 Cognitive Hierarchy Toolkit & Model Context Protocol (MCP) Server for Agentic Coding (Codex, Claude Code, Cursor)
pypi MIT ★ 1 -
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.
MIT ★ 7 -
Cognitive middleware for personal and enterprise AI agents: 14 MCP tools and a REST API for intent mirroring, persona/context profiling, decision support, memory, guardrail checks, and approval workflows. Deterministic offline engines with optional live Jev, SQLite/PostgreSQL, and Docker.
MIT ★ 1 -
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.
MIT ★ 49 -
Native Model Context Protocol (MCP) server providing typed state-action schema arbitration, deterministic action dispatch, and token-saving pre-escalation filters.
MIT -
Live two-way bridge between a running web app and Figma. Push screens as auto-layout frames; Figma edits go back into the code, code edits update Figma. A fork of Figma Console MCP.
NOASSERTION -
Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay, over the Chrome DevTools Protocol.
pypi MIT ★ 25 -
Jev-powered browser automation for agents through Python, CLI, MCP and Hermes; optional visual browsing and proxy support.
MIT ★ 1 -
Jev-gated Conductor cloud workspace router and stdio MCP server
npm MIT -
Native Mac computer use through persistent JavaScript, MCP, and TypeSafe Jev.
npm MIT -
Zero-token-output decision router MCP server powered by TypeSafe Jev
npm MIT