📡 MCP Radar

MCP servers for browser-agent

18 Model Context Protocol servers tagged browser-agent, ranked by stars. Updated daily. Browse all servers →

ThinkFlowLab/system1-agents

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

⭐ 132Python
jiawei686/jev-ultrafast-mcp

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 m

⭐ 18Python
alphaparkinc/genpark-sparkpage-synthesis-engine-skill

Dynamic search synthesis and Sparkpage layout compiler generating comparison matrices & HTML UI

⭐ 8Python
alphaparkinc/genpark-multi-model-cost-latency-router-skill

Dynamic intent and budget-aware multi-model Pareto router selecting from 70+ LLMs

⭐ 8Python
alphaparkinc/genpark-autonomous-browser-action-planner-skill

Autonomous web browser action planner mapping goals into resilient selector action sequences

⭐ 8Python
alphaparkinc/genpark-product-review-sentiment-analyzer-skill

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

⭐ 8Python
alphaparkinc/genpark-deep-research-consensus-engine-skill

Deep research multi-source consensus arbitration engine evaluating authority & contradictions

⭐ 8Python
Alpha-Park/genpark-autonomous-browser-action-planner-skill

Autonomous web browser action planner mapping goals into resilient selector action sequences

⭐ 7Python
Alpha-Park/genpark-deep-research-consensus-engine-skill

Deep research multi-source consensus arbitration engine evaluating authority & contradictions

⭐ 7Python
Alpha-Park/genpark-product-review-sentiment-analyzer-skill

Customer review aspect-level sentiment mining engine extracting satisfaction radar breakdown

⭐ 7Python
Alpha-Park/genpark-multi-model-cost-latency-router-skill

Dynamic intent and budget-aware multi-model Pareto router selecting from 70+ LLMs

⭐ 7Python
Alpha-Park/genpark-sparkpage-synthesis-engine-skill

Dynamic search synthesis and Sparkpage layout compiler generating comparison matrices & HTML UI

⭐ 7Python
tiliondev/waystone

Browser action recorder for automation: record a task once, replay it, or hand the folder to an agent

⭐ 5Python
littlejoely/omeety-terminal

A real local terminal in Edge/Chrome that gives Codex, Claude Code, Kimi Code, and any MCP CLI 41 local MCP tools through Browser Core v2.

⭐ 4JavaScript
scrollDynasty/multi-agent-browser-mcp

Multi-agent browser MCP runtime for isolated, persistent, parallel Playwright sessions. Run multiple AI agents without shared tabs or browser state.

⭐ 4TypeScript
HanHan666666/patchbridge-agent

Lightweight browser-side AI agent framework for legacy enterprise web apps—Java 8, Spring Boot 2, TypeScript, MCP/WebMCP, OpenAI-compatible LLMs, tool calling, streaming, audit, and persistence. 面向存量企

⭐ 3Java
Sachitt-AV-08/orvima

Why should Claude be the only one with a browser? Orvima gives any MCP-capable AI (Claude, Cursor, Copilot, your own agent) eyes and hands on your own Chrome or Edge — your logins, your machine, your

⭐ 3Python
saloni-garg/jev-max

The Jev browser agent that handles the real web: shadow DOM and iframe piercing, canvas fallback, uploads, multi-tab, MCP for any agent host.

⭐ 3Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.