"DOI" matching MCP servers:

Fetches documents by URL, DOI, ISBN, PMID or PMCID, and reports a block as a block, never as an empty success.

Enables QA to interactively inspect DOM elements in a visible browser, generate resilient Robot Framework locators and Page Objects, and validate selectors via natural language.

Drives a real Chromium browser to extract a page's DOM into compact Semantic JSON with Playwright-native locators, enabling AI agents to generate consistent, accurate Playwright tests.

Enables extracting precise data from web pages by parsing the DOM with CSS selectors and returning structured JSON, while also offering tools to inspect page structure, discover candidate selectors, and verify them without loading full pages into context.

MCP Server for Web2MD — convert webpage URLs to clean Markdown from Claude Desktop, Cursor, or any MCP-compatible agent.

Enables AI agents to record and time-travel through DOM mutations, inspect and interact with live pages, capture screenshots, and diagnose UI disappearance or layout changes through a 34-tool MCP interface.

It enables autonomous browsing clients to canonically compress rendered HTML into compact semantic trees, filter navigation traps, bind webform schemas, transform tables into typed records, and score interaction trajectories. Its tools operate locally over stdio with no runtime third-party requirements.

Enables real-time browser control and DOM interaction through a Chrome extension bridge, supporting navigation, snapshots, clicks, screenshots, and JavaScript execution.

Provides live web and document intelligence, including search, company news, scraping, crawling, structured extraction, document parsing, brand intelligence, screenshots, website monitoring, and batch jobs.

Enables local coding agents to send prompts to a user-authorized ChatGPT webpage through a browser extension and retrieve the final answer via MCP.

Enables autonomous web agents to prune raw HTML into accessibility-friendly semantic trees with 80%+ token reduction, auto-map form input schemas, convert HTML/Markdown tables into type-inferred JSON records, and score agent execution trajectories. Runs as a zero-dependency, stdlib-only MCP stdio server for Claude Desktop, Cursor, and Windsurf.

Gives Claude the ability to inspect and extract UI components from any webpage through a Chrome extension, enabling element discovery, style extraction, and design token analysis.

A Puppeteer-based server designed for remote debugging, E2E testing, and DOM inspection of frontend applications. It allows users to interact with page elements, capture screenshots, monitor network traffic, and execute JavaScript directly within a browser environment.

Enables AI assistants to control a browser for web automation tasks such as navigation, typing, clicking, and taking screenshots.

Browser-backed QA MCP server that lets coding agents test web apps, collect browser evidence, and return fix-ready reports before shipping.

Converts messy HTML into clean semantic markdown with integer IDs, enabling LLMs to navigate and interact with web pages efficiently using intent-guided filtering and diff-based updates.

Token-efficient browser automation for AI agents, filtering the DOM to only interactive elements and grouping them by page section, reducing token usage by 3-13x compared to Playwright MCP.