"Y Combinator" matching MCP servers:

基于百度图片搜索API，支持图片搜索、下载及格式转换的MCP服务器。

Enables MCP clients to submit HTTPS WeChat article URLs and receive parsed title, author, timestamp, and Markdown body through an external extractor, with clear errors for invalid paths, missing tools, timeouts, or access restrictions.

根据关键词获取小红书的热帖数据，需要钉钉扫码登录，配合 Chrome 使用。

基于MCP架构的微信公众号文章爬虫系统，支持AI智能体通过Selenium自动抓取微信公众号文章内容和图片，实现文章内容的智能分析。

Enables AI-driven job application automation for LinkedIn and SEEK platforms with intelligent cover letter generation, automated application submission, and application tracking management. Supports anti-detection measures and complies with platform usage policies for safe job hunting automation.

Fetches web content and converts HTML to markdown with robots.txt compliance and proxy support.

这是一个面向中文圈的MCP服务器，将中国互联网常用能力（如地图、快递、RSS、B站等）封装为标准MCP工具，方便AI Agent安全调用。

YouTube transcripts as token-efficient AI context. One fetch, cached. No yt-dlp, no API keys, no system dependencies. ~50 KB per video, instant re-reads from local cache.

Enables users to pull portfolio company lists from Y Combinator, a16z, Sequoia, Accel, and other investors or any portfolio page URL, returning one row per company with name, domain, website, description, and stage or batch. Runs on Apify and produces Clay-ready output, with YC results filterable by batch, industry, region, status, and search terms.

Real-time X (Twitter) data platform with 2 MCP tools covering 120+ REST API endpoints. Search tweets, look up users, get timelines, extract followers/likes/retweets in bulk, monitor accounts, run giveaway draws, and perform write actions (tweet, like, retweet, follow, DM). OAuth 2.1 authentication with PKCE.

A website audit MCP server that provides free tools to check on-page SEO elements like titles, descriptions, and images across up to 20 pages, and also validates robots.txt, sitemap.xml, and llms.txt accessibility.

Enables reading Y Combinator's Work at a Startup job postings and company details through a logged-in session, providing structured data to AI assistants.

Actualiza tu hoja de vida de CvLAC (MinCiencias) conversando con tu asistente de IA, sin llenar formularios a mano. Lee, agrega, corrige y borra formación, experiencia, proyectos, artículos, libros, software, eventos y perfil. Pregunta antes de borrar o de crear algo parecido a lo que ya existe. Corre en tu computador con Playwright: tus credenciales no salen de él. Proyecto no oficial.

Name: MyWebSearch Type: MCP Server (stdio + streamable-http/SSE) Repository: https://github.com/wtznicy/my-websearch npm: my-websearch (npx -y my-websearch@latest) Description: Multi-engine web search MCP server, CLI and local daemon — no API keys or registration required. Searches bing/baidu/csdn/juejin/sogou (domestic, no proxy needed in mainland China) and duckduckgo/exa/brave/startpage (overse

Controls Microsoft Edge to search X.com using an authenticated session, with validation to avoid returning stale content.

An MCP server that enables AI agents to access paid AI inference and web tools via HTTP 402 micropayments in USDC on Base, using the agent's wallet as identity.

A Node.js MCP server for X/Twitter that enables user profile queries, tweet search, tweet detail retrieval, and media downloads (images, videos, GIFs) via X's Web GraphQL API.

Use your signed-in Chrome through a local MCP server and companion extension. Supports tabs, navigation, forms, screenshots, and page reading, with a deny-all domain allowlist. Install: npx -y mcp-browser-extension@latest.

Enables fetching timestamped YouTube transcripts and compiling them into structured Cursor SKILL.md workflows through MCP tools.

A powerful MCP server that enables parallel Google searching with multiple keywords simultaneously, providing structured results while handling CAPTCHAs and simulating user browsing patterns.

Enables AI assistants to download sales reports from the AirREGI back office as CSV files by specifying the report type, store, and period, driving the user's own Chrome browser and reporting job progress and per-file results. Downloads are split by month and stored locally without any aggregation, with built-in safety checks and manual login handling.

Lets MCP clients read any public X post or full X Article as clean Markdown, including title, author, date, engagement, text, images, video links, polls, quoted posts, and the complete long-form article body.

MCP server that allows posting, deleting, and reading X (Twitter) tweets using your own browser session cookie, bypassing the official paid API. Includes tools for auth setup, tweet creation, deletion, timeline reading, and regex search.

为AI应用提供高质量网页搜索和结构化知识模态卡，涵盖新闻、天气、百科等领域。

Converts X (Twitter) posts into JSON, PDF, PNG, Markdown, or Slack/Discord messages using public endpoints, no API key or login required.

MCP server giving AI agents controlled residential-proxy web access with optional browser rendering and structured extraction from 60+ sites.

Enables AI agents to search live public X/Twitter posts and fetch recent posts from user profiles without API keys, using zero-configuration local MCP tools for Claude, Cursor, and Pi.

Wraps iguopin.com's public job board into standard read-only MCP tools (search_jobs and get_job), letting any MCP host such as Cursor, Claude Desktop, or Codex search listings by keyword, location, remote preference, and posting date, then fetch individual job details. Works as a standalone Node runner with polite rate limiting and no apply proxy or cookies.

Enables agents to read one public X/Twitter post from a status URL without cookies, returning post text, quoted content, links, and media URLs as untrusted data.

Enables DeepSeek Harness to run seller analytics and local Wildberries/Ozon marketplace tools — such as product search, data export and XLSX delivery — through an account login and browser extension, with per-job authorization of each tool call.

MCP server that scrapes Yandex Maps business reviews and company info, exposing them to AI assistants via three tools. No API key required, uses headless browser.

Obscura 헤드리스 브라우저 엔진을 활용한 개인 MCP 서버 — Claude Desktop 연동용

Enables reading public X/Twitter posts by URL or numeric ID and returning original structured data, including articles, quoted posts, and media fields, without requiring an X API key.

An ungated reimplementation of the 'Claude in Chrome' MCP bridge that exposes 22 browser-automation tools to any MCP client, driving the official Claude Chrome extension via native messaging without requiring a claude.ai login.

Enables AI assistants like Claude to drive a logged-in BOSS 直聘 recruiter dashboard through the Chrome DevTools Protocol, batch-searching candidates across many keywords, capturing resume screenshots and share links, deduplicating into a persistent local database, scoring and filtering candidates against YAML criteria, and exporting Markdown reports. It also supports sending greetings and tracking pipeline progress with resume-after-interruption.

让 Claude Code / Claude Desktop 等 AI 助手直接操作招聘后台，批量搜索候选人、截图查看简历、提取分享链接、筛选评分、导出报告并发送打招呼消息。它还能把候选人持久化到本地数据库，支持中断恢复和多关键词去重。

Enables Claude Desktop to scan, analyze, and track job postings from Hacker News and Y Combinator's Work at a Startup using a 24-tool MCP server with multi-stage filtering and resume-based ranking.

Enables AI assistants to automate a recruiter's BOSS 直聘 workflow by driving an already-logged-in Chrome browser through the Model Context Protocol, so they can batch-search and deduplicate candidates, capture Canvas-rendered resumes as screenshots and extract permanent share links, filter and score candidates from YAML criteria, greet them, and export Markdown reports while persisting everything to a resumable local database.

Enables AI assistants to automate a logged-in recruiter console over Chrome DevTools Protocol, running multi-keyword candidate searches, capturing and de-duplicating profiles into a local database, extracting share links, scoring and shortlisting applicants against YAML criteria, exporting Markdown reports, and sending greetings. A resumable pipeline keeps results across interruptions so work can continue where it left off.

Enables AI assistants to drive a logged-in recruiter account through Chrome DevTools Protocol to batch-search candidates across multiple keywords, screenshot Canvas-rendered resumes, extract share links, filter and score applicants, and export Markdown reports. Results are persisted to a local candidate database with deduplication and resumable pipelines.