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-powered browser automation for agents through Python, CLI, MCP and Hermes; optional visual browsing and proxy support.
MIT ★ 1 -
One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.
Apache-2.0 ★ 13 -
Jev-powered browser automation for Codex and Claude: native reasoning, continuous action loops, CLI, MCP and Chrome extension.
MIT ★ 2 -
Fast Jev browser agent for existing signed-in Chrome tabs via a local extension bridge and MCP
MIT -
Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.
npm MIT ★ 136 -
Browser automation where an LLM plans and Jev (Typesafe System One) makes every per-step decision. Library, CLI and MCP server.
npm MIT -
Hybrid browser automation tool combining a Jev-style fast policy with Browser Use Pi fallback, MCP integration, approval gates, audit logs, and independent verification.
MIT -
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 -
Let Claude code, chatgpt codex or control your own Chrome. Chrome extension + MCP server: Jev, TypeSafe's decision model, picks each click in ~0.5 s for a fraction of a cent. MIT, bring your own OpenRouter key.
NOASSERTION ★ 5 -
A browser agent where a small decision model (Jev, Clef) picks each action and a vision LLM steps in only when it is unsure. CLI, library and MCP server.
MIT -
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
npm MIT ★ 4 -
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 -
The Jev browser agent that handles the real web: shadow DOM and iframe piercing, canvas fallback, uploads, multi-tab, MCP for any agent host.
MIT ★ 3 -
Goal-driven browser exploration with Jev, compact evidence, and persistent supervisor handoff over MCP.
Apache-2.0 ★ 1 -
chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, Claude makes one devtools call there.
npm MIT -
A guarded MCP layer for Jev-powered browser decisions with isolated Playwright execution and explicit human approval.
MIT -
Claude thinks, Jev reacts: an MCP server that hands browser tasks from Claude to TypeSafe's Jev (~100 ms per decision).
MIT -
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 -
chrome-devtools-mcp plus one tool: Jev walks the browser to the spot, your agent makes one devtools call there.
npm MIT ★ 1 -
Fast Jev browser MCP server: Jev (TypeSafe System One) drives a real Chrome step by step for AI agents and hands back early when unsure.
npm MIT -
Runs the jev-browser-use click loop in Google Chrome for any MCP client.
MIT ★ 1 -
cloakbrowser-agentactive
Jev-powered stealth browser agent: TypeSafe Jev decides each step, CloakBrowser carries it out. MCP server, CLI and Python API.
pypi MIT -
Fast browser hands for coding agents: the agent names an outcome, Jev (TypeSafe's decision model) picks each click in about 300 ms. MCP server, Claude Code plugin, library and CLI; works in a browser it launches or in your own Chrome or Edge.
npm MIT -
A bounded Jev System-1 browser tool for Pi, OpenCode V2, Amp, and MCP, powered by agent-browser
npm AGPL-3.0 ★ 2 -
Jev-powered stealth browser agent. TypeSafe Jev decides each step in ~0.3 s, CloakBrowser carries it out like a human. MCP server, CLI and Python API.
MIT ★ 6 -
Open-source browser automation for Codex and MCP. Jev/Laya decisions, Playwright execution, Brave sessions, persistent extension authentication and verified workflows.
MIT ★ 4 -
Hand browser goals to TypeSafe Jev from any coding agent: an MCP server and CLI that returns one short, checked summary
npm MIT -
Hand a browser goal to TypeSafe Jev; get a short verified summary back. MCP server + CLI.
npm MIT -
Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes.
MIT ★ 25 -
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics
Apache-2.0 ★ 183 -
Claude thinks, jev clicks: a fast browser tool (and MCP server) for Claude Code. 5-6x faster web tasks than screenshot-driving, with before/after benchmarks.
MIT -
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.
npm MIT ★ 6 -
🐦 Colibri — the hummingbird browser for AI agents (Claude, Copilot, Cursor, Codex…): pages as compact text, not screenshots. 89x fewer tokens, local Jev-style form engine, 0 API keys.
MIT ★ 3 -
Jev MCP server: a decision layer for Claude Code, Codex, and Cursor built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of your agent's context, and a safe headless browser.
npm MIT -
MCP server that gives agents a browser that finishes tasks itself: Jev plans each step, real Chrome executes, results come back verified.
npm MIT ★ 2 -
Baton Agent Orchestrator — jev CLI + web dashboard that turns ideas into reviewed, tested code. Multi-provider dispatch (Claude Code, Codex, OpenRouter) across plan-validate-code-test-integrate, with autonomy modes, cost-aware routing, Kanban board, fleet view, browser preview with takeover, MCP servers, recursive learning and a quality gate.
Apache-2.0 -
Delegate browser operations to an ultra-fast MCP server, executing full page tasks in seconds with one tool call.
MIT -
A fast browser-use layer for CLI coding agents: MCP server, CLI and Python API. This package is a launcher; it runs the Python tool through uv.
npm MIT -
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 -
Serveur MCP pour piloter Firefox avec Claude : Jev (TypeSafe) choisit les clics, Claude planifie. Benchmark inclus.
MIT ★ 1 -
Typed semantic filtering for AI agents: turn retrieved records, code and logs into compact evidence with source IDs. CLI · Python · TypeScript · MCP.
npm MIT ★ 1 -
Goal-driven AI agent that records walkthrough videos of any web app and writes the user guide. Powered by Jev (TypeSafe AI) + Playwright, driven from Claude Desktop via MCP. Open-source alternative to Supademo/Scribe and manual testing.
MIT -
A extension chrome mcp server allow AI agent full remote "same" playwright
npm MIT ★ 15 -
BrowserClaw - Control your everyday Chrome browser from AI agents, without losing logins or focus
AGPL-3.0 ★ 41 -
Autonomous career agent, ATS resume tailor, and job search copilot.
pypi MIT