"Tools and Extensions for Web Browsers" matching MCP servers:

Enables cross-browser mobile-first responsive layout auditing and browser automation, including overflow detection, tap target checks, viewport/media query introspection, and screenshot matrices via MCP.

Enables generating JSON Schema from sample data, generating TypeScript types, validating data against schemas, creating mock data from schemas, and comparing schemas for differences.

Webhook management and testing tools for AI agents. Provides tools for sending, validating, generating, and debugging webhooks.

MCP server that lets AI editors execute JavaScript, read console output, and simulate clicks/input on static web pages. Supports multiple browser pages and can be deployed remotely via HTTP transport.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Enables validating JSON/JSONC, getting/setting values with jq-like paths, pretty-printing or minifying, validating against Ajv JSON Schema, and diffing local files or inline strings without network calls.

Enables AI agents to rapidly drive and inspect real web pages through persistent browser sessions, using accessibility-tree snapshots and DevTools-grade diagnostics to identify and diagnose issues.

Enables AI assistants to inspect, debug, and test web pages using Playwright. Provides comprehensive DOM inspection, visibility debugging, layout validation, and element finding capabilities in real browser environments.

Enables coding agents to run Playwright e2e tests, validate Supabase RLS policies with role-based SQL, typecheck TypeScript, execute npm scripts with parsed test output, and validate Next.js builds, all through a structured MCP interface.

An MCP server that gives AI agents the ability to inspect, observe, and automate WKWebViews on connected iOS devices via Safari Web Inspector.

Provides Codex and other MCP clients a local web debugging server that coordinates a browser session, JavaScript debugger, bounded runtime evidence, and reproducible flow verification for vanilla HTML/JS projects.

A Node.js-based frontend security audit tool that performs comprehensive dependency security audits for both local projects and remote repositories. Generates detailed Markdown reports with vulnerability detection, risk assessment, and fix recommendations.

Provides web accessibility analysis and color blindness simulation using axe-core and Puppeteer, enabling detailed accessibility checks and visual simulations based on WCAG guidelines.

MCP server providing code review, auto-fix, test running, linting, formatting, and refactor suggestions for Claude Code.

Review AI-generated HTML slides or reports in the browser, anchor comments to specific passages, and have the agent fix them via MCP, with tools for inspection, commenting, layout checking, and export to PDF/PPTX.

Provides 32 remote tools that let agents validate common data formats, optimize or minify code and content, and generate synthetic test data such as fake records, IDs, and passwords.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.

Enables an agent to locate embedded Flash or Java games (on live pages or in the Internet Archive), inspect whether they can run, fetch the Ruffle or CheerpJ runtime, package a self-contained static site, and verify playback in a real headless browser. Every step produces an evidence bundle so revived games can be hosted on any static host with claims backed by recorded results.

Code linting and style checking tools for AI agents, exposed as an MCP server. Supports style checks, naming conventions, complexity analysis, dead code detection, and import analysis.

Exposes read-only and write probes over a remote Streamable-HTTP /mcp endpoint so users can verify that ChatGPT Web discovers and calls remote tools, and test whether write actions actually execute on their plan. Real HWPX document editing is not yet supported; this P0 release only measures connectivity and read/write action boundaries.