Selenium MCP

git clone https://github.com/gaforov/selenium-mcp.git cd selenium-mcp npm install npm run build

Then point your MCP client atnode /absolute/path/to/selenium-mcp/dist/server.js.

The agent chainsstart_browser→navigate→get_title→take_screenshot→stop_browseron its own — no scripting needed.

- Node.js 20+
- Chrome, Firefox, or Edge installed (Selenium Manager provisions the matching driver automatically)

Most Selenium MCP servers wrap WebDriver's basic commands. This one adds the layer that makes agentsreliable:

- Snapshot-first workflows—capture_pagereturns a page snapshot with stable element refs the agent can act on directly, no brittle selector guessing
- Selector hints— persist working locators per domain so repeat automations get faster and more reliable over time
- Batched execution—batch_executeruns constrained multi-step sequences in a single tool call, cutting round-trips
- Multi-session— create, select, list, and destroy parallel browser sessions
- Agent-friendly errors— every response is structured and validated with zod, so agents can recover instead of stalling
- Optional tracing— NDJSON trace of every tool call for debugging and auditing

- browser-status://current— live browser/session status
- accessibility://current— accessibility snapshot of the current page

Enable lightweight NDJSON tracing of all tool calls:

SELENIUM_MCP_TRACE=true SELENIUM_MCP_TRACE_PATH=./logs/selenium-mcp-trace.ndjson

IfSELENIUM_MCP_TRACE_PATHis omitted, the default islogs/selenium-mcp-trace.ndjson.

npm run typecheck npm run build npm test

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Control your real Chrome from Claude Code. 29 tools including CAPTCHA solving, file upload, multi-session, and human-in-the-loop.

Automate web browsers using Selenium WebDriver via MCP.

MCP tools for crawler-readability and discovery-file diagnostics, including crawler-visible HTML inspection, raw-vs-rendered comparison, and discovery-file checks.

Automated QA testing for websites to find UI bugs, broken links, and accessibility issues.

Official Playwright MCP server for browser automation, page inspection, screenshots, and web interaction from Claude, Cursor, and other AI agents.

Render website screenshots with ScreenshotOne

Attaches to existing browser sessions using the Chrome DevTools Protocol for automation and interaction.

Help your AI agent finish more browser tasks.