Browser automation agents

Dobeu-tech-eco/dobeutech-claude-code-custom

Agent

Part of dobeutech-claude-code-custom

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

ahelme/mcp-claude-code-browser-tools

Agent Claude Code

MANE Agent I - Content Extraction Specialist for browsergetcontent tool. Expert in DOM analysis, HTML extraction, semantic content processing, and timeout resolution. Use when fixing browsergetcontent tool, implementing content analysis systems, or optimizing large content handling.

simon-ami/zen-devtools-mcp

Agent

Part of zen-devtools-mcp

Agent for running E2E tests on web applications. Navigates pages, fills forms, clicks buttons, and verifies results.

simon-ami/zen-devtools-mcp

Agent

Part of zen-devtools-mcp

Agent for browsing and extracting structured content from web pages. Navigates pages, handles pagination, and returns structured data.

gitgitWi/council-flow

Agent

Part of flow

Frontend-only browser QA tier — drive a real browser to verify a web change actually renders, responds to events, and makes the right network calls. Use after a web-frontend change (alongside code review, in parallel) to confirm the UI works in a browser, not just that tests pass. Prefers agent-browser, falls back to…

leonhoffmann86/team-sprint

Agent

Part of sprint

STAGE 2 (scaffold — not yet wired into the loop). Verifies UI implementation in the browser via screenshots + a11y tree. Use only for items with a frontend/UI part; Figma optional.

ne11nn/cantos-plugin

Agent

Part of cantos

General-purpose browser automation agent using playwright-cli. Use when a task requires real web interaction — navigating pages, clicking, filling forms, handling authentication, or extracting structured content that WebSearch cannot access. Do not use for simple information lookup; prefer WebSearch first.

morodomi/dev-crew

Agent

Part of dev-crew

A browser-based security-testing agent that discovers web application URLs and endpoints, including routes created while the page runs.

WaynePluto/local-web-search-agent

Agent

A local web-search assistant that searches with Bing and reads relevant web pages before answering.

enihcam/opencode-webmcp

Agent

Single-file MCP server bridging MCP clients (OpenCode, Claude Code) to Chromium's WebMCP API. Connects via Puppeteer + CDP, discovers tools registered via document.modelContext on the page, and exposes them as MCP tools.

huuanh20/awesome-ai-agent-skills

Agent Claude Code

General-purpose Playwright screenshot agent. Auto-detects capture mode from inputs — section-centered viewport (show-off), element clip, or full page. Optional BGSOURCE triggers composite step (background photo + card overlay). Spawned by /show-off and any task needing screenshots.

RaghupathiReddySeetaramula/Playwright-MCP-Agents

Agent

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

priyshi/playwright_mcp_pr

Agent

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

priyshi/playwright_mcp_pr

Agent

Use this agent when you need to create comprehensive test plan for a web application or website.

pochtmanr/argus-mcp

Agent

Argus is an anti-detect browser. A profile is an isolated browser identity with its own fingerprint, proxy and cookie jar. This project can drive those profiles either as MCP tools or over plain HTTP.

pochtmanr/argus-mcp

Agent

Argus is an anti-detect browser. A profile is an isolated browser identity with its own fingerprint, proxy and cookie jar. This project can drive those profiles either as MCP tools or over plain HTTP.

DanielBirk04/capusqa

Agent

Part of capusqa

Plays one human persona testing a macOS app through the capusqa MCP daemon. Spawned in parallel for a human run (by the CapusQA runner / autopilot), one per persona-session. Claims tasks from the run's work queue and drives the app via observe/click/type tools while staying in character.

felipestenzel/mcp-tap

Agent Claude Code

Use this agent when you need to create, debug, or improve end-to-end tests using Playwright. This includes writing new test suites, fixing flaky tests, adding visual regression testing, configuring cross-browser test matrices, setting up CI/CD pipeline integration for tests, or refactoring existing tests for better…

BAM-DevCrew/maxerviker-firefox-devtools-mcp

Agent

Part of firefox-devtools-mcp

Agent for browsing and extracting structured content from web pages. Navigates pages, handles pagination, and returns structured data.

openlearnia/OLTestStack

Agent Cursor

Specialized agent for running browser tests via OLTestStack MCP tools. Use proactively when asked to test web pages, login flows, CRUD operations, smoke tests, or UI verification. Invokes olteststack MCP tools directly — never simulates browser actions without calling MCP.

m4ttstack/fast-browser

Agent

Part of fast-browser

Drives a delegated multi-step browser task through Fast Browser and returns only the distilled result.

Akakaui/visual-browser-agent

Agent Claude Code

Study rendered websites, interactions, responsive layouts, and animations using the visual-browser MCP server. Use when visual evidence is needed.