Provides AI coding assistants with on-demand access to component specs, test scenarios, accessibility requirements, and build guides from the Web UI Component Specification.
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 MCP clients like Codex to delegate coding tasks to DeepSeek Harness, reusing the same Web-visible session for feedback and keeping the conversation in the Harness Web UI.
Enables AI coding assistants to validate HTML/CSS markup using W3C APIs, perform technical SEO audits, check broken links, and validate JSON-LD schemas directly in local workspaces.
Provides deterministic, read-only design knowledge for AI coding agents to help them choose visual directions, plan UI states, and compose design tokens, all without network access.
A TypeScript-based MCP server that enables AI assistants to execute HTTP requests with full control over methods, headers, and body content. It facilitates seamless interaction with web APIs and endpoints through a versatile tool that handles automatic JSON formatting and response truncation.
Enables AI coding agents to set up the kit and build pages with it by serving each release's own docs data: searching and describing components, producing install code for a given setup, returning class and content conventions, and checking pages for unknown classes, hooks and missing files. It reads only public docs, with no sign-in or stored data.
Enables any MCP client to browse, triage, search, read, and drive pi coding agent sessions through Pi Web's HTTP API via 25 tools. Supports listing and filtering sessions, reading transcripts, flagging conversations awaiting input, sending messages and waiting for replies, inspecting project diffs, and forking, renaming, or deleting sessions over either stdio or Streamable HTTP.
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.
Enables agents to inspect localhost web applications through Chrome DevTools Protocol by listing Chrome targets, attaching to a page, capturing and querying network, console, navigation, and WebSocket events, and managing ephemeral sessions.
A local Python WebSocket bridge and browser extension that securely connects web AI chats to local Model Context Protocol (MCP) servers. It enables web-based AIs to execute local tools with granular permission controls, providing the same powerful tool and system access typically exclusive to desktop agent harnesses like DeepSeek Harness, Claude Code, Codex and more.
Enables web performance analysis using Google PageSpeed Insights and Chrome UX Report APIs, providing compact metrics and diagnostics without local browser automation.
Free remote MCP for Core Web Vitals metrics by CMS, CDN, and framework (Chrome field data + multi-site crawl). No auth. Endpoint: https://www.corewebvitals.io/api/state-of-cwv/mcp
Enables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Serves as a demonstration and educational project for building MCP servers with external API integrations.
Enables managing OVHcloud Web Hosting services via Model Context Protocol, providing tools to list, configure, and manage hosting resources through natural language.
A dual-transport MCP server enabling anonymous free web search via Parallel (default) or Exa (backup), with no API keys or DSH dependency, for Claude Code, Codex, and any MCP client.
Enables ChatGPT to work with a local Windows development environment through MCP, including file and code operations, terminal commands, Git, browser and desktop automation, and task-specific skills. Also supports long-running task management and isolated account workspaces.
Enables ChatGPT plugins and other MCP clients to fetch live web pages and documents as Markdown and to call HTTP APIs via self-hosted Cloudflare Workers.
Connects ChatGPT Web to a local development environment, enabling file reads and patches, shell execution, plan updates, and isolated worktree coordination through permissioned MCP tools.
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.
Enables ChatGPT to save conversation attachments, generated files, and images directly into a configured local macOS project directory with OAuth-secured MCP access.
Enables pixel-perfect website cloning from within the IDE by extracting real source code, styles, and assets, and assembling them into a React project with live preview.
Enables agents to scan web UI screens, follow login and test-case flows, and generate verified XPath locator .properties files with one unique locator per element, including support for iframes, SSO/MFA, proxies, and internal networks.
Generates all required web app icons and manifest files from a single source image with framework auto-detection. Supports Next.js App Router, traditional web apps, and PWA standards with zero configuration.
Delivers curated documentation, quickstart commands, and stack recommendations for modern full stack web development through MCP-enabled AI assistants.
Enables Antigravity IDE to delegate coding, debugging, and architecture work to an already logged-in Gemini, Claude, ChatGPT, or DeepSeek web session, then applies the returned changes directly to workspace files over a local WebSocket bridge.
Enables users to select UI elements on localhost pages and send fix requests to MCP-compatible coding agents, which retrieve the captures and edit the code, with masking of sensitive values.
Enables LLM agents to drive a selector-free browser through natural language, so they can debug styling and console errors, map and document web apps, and generate or run end-to-end and exploratory tests without screenshots.
Enables AI coding assistants to use Web Gemini as an on-demand subagent for multi-turn text and multimodal Q&A, persistent named sessions, model selection, and health checks, with process-safe session storage and secure authentication.
Enables AI agents to read any web page as clean Markdown and inspect its metadata, structure and technology stack, plus check redirects, TLS certificates, security headers, robots.txt, sitemaps, feeds, domains, SEO, broken links, email authentication (SPF/DMARC/DKIM) and SSO (SAML/OIDC). It also provides developer utilities such as cron, regex, color, Unicode and time-zone tools along with Hyperliquid perpetuals market data, all hosted remotely on Apify with pay-per-call pricing.
Enables Antigravity IDE to query Google Gemini 4 High (Argon) with deep reasoning through Gemini Web, including multi-account quota failover and automatic cookie renewal.
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.
Enables AI coding assistants to run live URL DAST, source-code SAST, secret hunting, dependency CVE checks, and generate context-aware patch diffs over stdio.
Enables coding agents to publish HTML artifacts that users can review and comment on in a sandboxed browser viewer, with feedback loop support for iterative versions.
Enables AI coding agents to autonomously interact with and test web applications in a real browser, providing DOM/Accessibility tree extraction, runtime telemetry, screenshot capture, and Markdown test reports.
MCP server enabling Cursor to delegate complex coding tasks to ChatGPT Web (GPT-5.6 Sol High) via Temporary Chats, supporting parallel batch reviews and up to five concurrent sessions.
Exposes an authenticated local runtime over OpenAI Tunnel so ChatGPT can inspect authorized Windows workspaces, read bounded Git status and diffs, submit and cancel Codex CLI tasks, and use workspace Skills. It also brokers connections to optional loopback stdio or HTTP MCP services, such as Stata and Zotero, with explicit tool allowlists and loopback-only access.
Provides local web search (Baidu, Bing, 360, Sogou), page scraping to markdown, and image description via LM Studio vision models, all without external APIs and with disk caching.
Provides OAuth-protected remote access to an existing Open Brain, forwarding approved tool calls from Gemini Spark and Perplexity web clients without altering the upstream system.
A lightweight web scraping server that allows Claude Desktop users to extract various types of data from websites, including text, links, images, tables, headlines, and metadata using CSS selectors.
Enables AI agents and MCP clients to fetch web pages and distill them into clean, token-efficient markdown by stripping cookie banners, navigation bars, and ads. Runs with zero external dependencies over JSON-RPC stdio, delivering deterministic sub-millisecond results without LLM round-trips.
16-tool MCP server for Google PageSpeed Insights & Chrome UX Report APIs. Analyze, compare, and optimize web performance directly through Claude, Cursor, or any MCP-compatible AI client.
Deterministic encode, decode, hash and convert for agents, on the same pipeline engine as the String Utility Belt web app, CLI and editor extensions: a pipeline built and checked in the browser runs unchanged from its share link. Base64/hex/URL, JWT, hashes, JSON/YAML/CSV/XML, dates and regex; tools to search, describe and run utilities or whole pipelines, and to detect input formats. Runs locally
Gives local and cloud LLMs live web grounding as four MCP tools: web_search, fetch, deep_search (a token-capped, cited evidence pack sized to a small context window), and research (an agentic search-and-read loop). Flat monthly pricing, no query content stored.
Publish a web game to neme.world from a coding agent: upload a preview, make a version live, roll back to an earlier one, and read its play numbers. Games open from a link and play at once, on a phone or a computer.
Deep Research infrastructure for AI agents. Search the web, read pages incrementally, follow source links, and collect relevant evidence across multiple sources. Web search runs through your own SearXNG instance, while the agent remains in control of research planning and reasoning. Cluefinch runs locally over MCP stdio.
Serves the review notes left at lines of a diff in seam, a terminal diff viewer, to an agent with the code around them. The agent answers each note, and the answer shows in seam at that line.