Browser Automation MCP servers

LinkedIn for AI agents from your own Chrome session: search, profiles, lists, outreach queue.

Web automation through Selenium WebDriver.

MCP server for Glyphic — the model emits typed JSON, Glyphic renders it deterministically as SVG/PNG. No DSL, no headless browser, 18 diagram types for LLMs and agents.

LinkedIn via an authenticated browser session: profiles, people/job/company search, feed, messaging and gated writes (connect, post, react, comment).

Control Chromium-based browsers such as Arc, Vivaldi and Brave via an extension: navigate, click, read pages, run JavaScript and record GIFs.

Website testing with Playwright: assertions, auto form-fill, persistent logins, network mocking, and accessibility, SEO, GEO and Lighthouse audits.

Co-browse for coding agents: pick elements in the browser, write a note, Send — the context lands in the agent's chat. MCP server with 6 tools.

Evidence-grounded web research: verify claims on pages with citations, confidence bands and policy reports, and synthesize multi-page sessions.

Search Amazon India via scraping: cheapest-in-stock and value picks, product details (price, MRP, rating, stock, seller) and Keepa price history links.

Fetch web content as clean Markdown through a multi-tier fallback chain, handling tweets, YouTube, arXiv, PDFs and regular pages.

Browser automation using the user's Chromium session — JS execution, auth, and anti-bot support.

Microsoft Graph CLI + library — typed Bun/TypeScript wrapper around 200+ Graph operations (read + on-the-fly PDF/markdown conversion + federated Microsoft Search) reachable from a Teams browser-OAuth token.

MCP server for DoorDash - let AI agents order food delivery autonomously with browser-based ordering

Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.

Real physical SIMs for AI agents: SMS verification, number rentals, proxy bandwidth and Cloud Browser sessions, plus x402 USDC deposits. 145+ countries, 2500+ services.

Record your authenticated browser session (rrweb DOM, console, network) to local SQLite with PII masking, so coding agents can query it or drive the browser.

Self-hosted stealth browser built on a Firefox fork with fingerprint spoofing, shadow-DOM-aware page reading, login state detection and evidence recording.

Web scraping: clean content extraction, CSS-selector scraping, Playwright screenshots, link and metadata extraction, and Google search.

Headless DHI MIKE+ urban-water modelling: model inspection, parameter editing, simulation runs with QA status, .res1d results reading and plotting.

Security-hardened Chrome automation and logins with post-quantum encryption, a credential vault, memory scrubbing and audit logging.

Bridge a live Chrome browser to your agent: 150 tools for capture, extraction, and observation.

Manage Storyblok headless CMS stories, components, assets, workflows, releases and more.

Self-hosted stealth Chrome automation via Patchright: parallel persistent profiles, encrypted credential vault with 2FA, and prompt-injection scanning.

MCP server for AWS Pricing Calculator — create estimates, get shareable links, and retrieve actual AWS-calculated costs. Supports all 400+ AWS services, EC2 Savings Plans, sub-service resolution, and headless browser cost verification.

Live+headless Aseprite MCP: Unity export, art-QA, tilemaps, in-editor dialogs, update-aware

Headless browser automation and web scraping via the Browserless smart scraper API.

Anti-detection browser automation with Camoufox - stealth Firefox for web scraping

E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.

JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

Search, read, create, edit and sync Joplin notes and notebooks via a headless Joplin sidecar.

Real signed-browser automation for AI agents, over a local stdio MCP server.

Pure-Go browser for AI: fetch pages, render JS without Chromium, return clean Markdown over MCP.

MCP server for web scraping — extract clean markdown, links, and metadata from any URL. Zero auth. Free alternative to Firecrawl.

Code-aware browser testing that reads routes, forms and existing tests, runs Playwright scenarios, and keeps regression history and screenshot reports.

Backlink lookups, competitor gap analysis and outreach-target discovery over the public Common Crawl webgraph via CrawlGraph.

Local-first crypto portfolio aggregation across Bybit, Binance, EVM and Solana wallets and Polymarket, with read-only credentials in the OS keychain.

Delegate real-world actions to Hermes Agent: research, browser workflows, messaging, scheduling and skills, with risky actions requiring approval.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic. Yours to own.

Render any URL or raw HTML as PNG, JPEG, WebP or PDF, with batch processing, geo-targeting and async webhooks.

Local-first shared memory and task coordination for AI coding agents. Go daemon plus headless CLI.

Drive your real Chrome over MCP: real logins and cookies, multi-tab automation, deny-all by default.

Undetected Chrome automation via nodriver for anti-bot protected sites: accessibility snapshots, input automation, network inspection and persistent sessions.

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.

AnyCrawl MCP Server, Powerful web scraping and crawling for Cursor, Claude, and other LLM clients via the Model Context Protocol (MCP).

MCP server for creating, running, inspecting, and scheduling Figranium browser automations.

Control visible, persistent Hronaut browser workspaces through a local MCP connection.

Open-source MCP server for browser automation — gives AI agents control of a real Chrome browser via extension

Playwright-style MCP to inspect, control, and debug PySide6 desktop GUIs.