MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
AI crawler checker: Chrome extension + MCP server that shows which content GPTBot, ClaudeBot and other AI crawlers can't see because it needs JavaScript (raw HTML vs rendered).
AGPL-3.0 -
AI crawler checker MCP server: shows which page content GPTBot and ClaudeBot miss because it needs JavaScript. Raw HTML vs rendered DOM, from the Unrendered Chrome extension.
npm AGPL-3.0-only -
Fetch web pages and extract clean, structured content as Markdown. Render JavaScript-heavy sites, capture screenshots or PDFs, and automate browsing safely in isolated sandboxes.
smithery -
Renders JavaScript-heavy pages in a real browser so agents can read them.
MIT -
spa-reader-mcpgithub.com/xxo47oxx/spa-reader-mcpupdated this year
MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content
npm MIT -
MCP server for Obscura headless browser — CLI wrapper for AI agent integration with web scraping, JavaScript rendering, and browser automation
Apache-2.0 ★ 4 -
webgithub.com/GuionAI/webactive
A web research toolkit with multi-provider search and clean Markdown extraction from static and JavaScript-rendered pages, plus public code and library docs search—available via CLI and MCP.
Apache-2.0 ★ 1 -
Render JavaScript-heavy pages in a real browser so AI agents can read them. CLI, MCP server, and HTTP service.
npm MIT -
Visual CLI for agents. Deterministic SVG diagrams, tables, and charts with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.
Apache-2.0 ★ 61 -
Visual CLI for agents. Generate deterministic SVG diagrams, charts, and tables with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.
pypi Apache-2.0 -
Firecrawl Web Scraping Serverno update data
Enable advanced web scraping, crawling, and content extraction with support for JavaScript rendering, batch processing, and smart filtering. Perform deep research and structured data extraction using LLM-powered tools. Monitor credit usage and handle rate limits automatically for efficient and reliable web data integration.
smithery -
Free, open-source SEO crawler and Screaming Frog alternative. Crawl any site locally with no URL limit: technical SEO audit, JavaScript rendering, AI fixes, MCP server.
MIT ★ 1 -
markdown-for-agents-mcpgithub.com/johnnyfoulds/markdown-for-agents-mcpupdated this year
MCP server for AI agents — fetch any URL with full JavaScript rendering (Playwright/Chromium) and convert to clean, token-efficient markdown. Works on React, Vue, Angular, and any JS-heavy page.
npm MIT -
claude-plugingithub.com/customjs/claude-pluginupdated this year
Official Claude Code plugin for CustomJS, host HTML pages, generate PDFs, capture screenshots, scrape JS-rendered websites, and run sandboxed JavaScript directly from Claude via the Model Context Protocol (MCP).
MIT -
MCP server for AI agents: free keyless web search, plus pay-per-call extract (URL to markdown), JavaScript render and search+read over x402 (USDC on Base). No API key.
MIT -
crawlbase-mcpgithub.com/crawlbase/crawlbase-mcpupdated this year
Crawlbase MCP Server connects AI agents and LLMs with real-time web data. It powers Claude, Cursor, and Windsurf integrations with battle-tested web scraping, JavaScript rendering, and anti-bot protection enabling structured, live data inside your AI workflows.
★ 60 -
The measurable image + document toolkit for JavaScript. On flat art -- logos, icons, UI, screenshots, pixel art -- the SVG is bit-exact: SSIM 1.0000, zero differing pixels, verified by rendering it back. On photographs it leads potrace, imagetracerjs and
npm MIT -
Free, open-source CLI and MCP server that checks whether AI crawlers (GPTBot, ClaudeBot, PerplexityBot, CCBot) and search engines can access your website: robots.txt, llms.txt, sitemap, JSON-LD, meta tags, JavaScript rendering and Common Crawl presence. Runs locally.
npm MIT -
render-fetchgithub.com/sub-techie09/render-fetchupdated this year
Drop-in upgrade to Claude's WebFetch — auto-detects static vs JS-rendered pages and returns clean markdown
npm MIT -
Agentic-first 3D modeling: AI agents build geometry over MCP, a tiny pure-JS CPU rasterizer renders it. Zero dependencies, no GPU.
MIT -
Resilient multi-provider web search & content extraction for Claude Code, DeepSeek Harness, and any MCP host — quota-aware failover, JS rendering, and a CLI.
Apache-2.0 ★ 2 -
Verify AI outputs in real-time to ensure code and data accuracy before execution with this Model Context Protocol server.
Apache-2.0 -
Figma to pixel-perfect code, as an MCP server. Converts a frame deterministically, then renders your code in Chromium and pixel-diffs it against the design until it converges.
npm MIT ★ 1