"How to fetch or scrape data from a website for use in training an LLM" matching MCP servers:

Launches multiple Browser-Use agents to automatically test websites for UI bugs, broken links, accessibility issues, and other technical problems on both live and localhost sites.

Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts.

Runtime access for AI coding agents to observe and control Android and iOS apps.

Enables auditing any public website, returning a scored plain-English report that flags issues costing customers, covering speed, phone experience, search visibility, contact options, writing quality, and modernity.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

This server performs a comprehensive analysis of a website by fetching its HTML and scoring it across five categories: performance, SEO, design, functionality, and technology. It enables users to identify technical strengths and weaknesses in a webpage's structure and health.

Free church website audit: an MCP server that checks a church homepage for mobile, speed, SEO and first-time-visitor basics.

MCP server that provides tools for evaluating LLM agent reliability, including adversarial task generation, automated LLM-as-judge assessment, and confidence statistics.

Enables AI agents and MCP clients to drive real Chrome, Edge, Brave, and Firefox browsers through native automation protocols. It exposes tools for navigation, page snapshots, form filling, clicks, screenshots, console/network inspection, and tab management.

Browser control for Claude Code, on Firefox.

Enables MCP clients to open websites, capture screenshots at multiple breakpoints, and run automated design audits for issues like overflow, small tap targets, low contrast, missing alt text, tiny text, and clipped content.

A local MCP server that packages LLM evaluation gates as reusable CI/CD primitives, enabling AI agents to run datasets against models, score responses, and enforce quality thresholds.

Enables AI assistants to scan project dependencies and Infrastructure as Code files for security vulnerabilities and misconfigurations. It also provides automated fixing capabilities to remediate identified security issues.

Provides a universal bridge to interact with any OpenAI-compatible LLM API (local or cloud), enabling model testing, benchmarking, quality evaluation, and chat operations with performance metrics.

MCP server to mock OpenAI, Anthropic, and Google Gemini responses for testing AI integrations without real API keys or token spend.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

Enables provider-agnostic LLM discovery, capability testing, stability screening, and AIPerf benchmarking through MCP, with persistent SQLite history.

Reproduces a race condition in mcp-use dev where tool results are dropped when the handler completes after the widget iframe loads.

The iOS Simulator for coding agents: builds and runs Xcode projects, reads the screen as compact text, taps and types by label, and runs XCTest and XCUITest case by case.

Enables coding agents to evaluate a single model over a golden set with trap cases, reporting accuracy overall and on traps, mean latency, cost per request, and failing cases. Also compares a baseline against a candidate model and returns a pass/fail gate verdict with failure reasons, so a model swap can be checked before it ships.

Enables local, cross-provider preflight validation of LLM integration changes—model, prompt, structured-output, and provider-call modifications—with no-spend checks, evidence on speed, tokens, and cost, and explicit human approval before paid runs.

Lets any MCP client, such as Claude, browse attack suites and probes, run a full assurance assessment with all reports written out, send custom prompts or multi-turn histories and get leak, PII and refusal checks back for adaptive attacks, and read findings from an earlier assessment. This enables agent-driven red-teaming of a chatbot, RAG app or AI agent without leaving the chat client.

Enables macOS GUI automation via screenshots, mouse/keyboard control, accessibility tree inspection, and app/window management.

Enables turning requirements documents into RFCs, functional test scenarios, and a traceability matrix, with tools to parse, diff, and verify coverage.

Enables headless Blender asset QA and FBX reimport verification for game and 3D asset pipelines, checking mesh count, material count, and naming prefixes with deterministic JSON results.

Automates the conversion of Figma designs into TypeScript React components and integrates with GitHub to create pull requests for the generated code. It includes visual regression testing with Playwright and accessibility validation to ensure implementations match the original designs.

Enables Baldur's Gate 3 modders to look up game data across base-game and mod layers, run static lint checks on stats and progressions, test changes in a running game through the Script Extender, and export mods for Larian Toolkit/mod.io publishing. It also packs, deploys and restarts the game so mods can be iterated on without leaving the assistant.

Enables coding agents to observe and operate Android devices through ADB and uiautomator2, supporting screenshot capture, UI hierarchy access, and actions like tap, swipe, and text input.

Enables OpenCode to safely automate and verify Windows desktop and web browser interactions through 83 MCP tools, including UI automation, screenshots, visual diffing, workflow recording, and secret handling, with strict allowlist-based security.