MCPs + Skills
Stacks
Curated stacks
Frontend Developer
Build interfaces, test in a browser, and work with project data.
View stack →02Research
Find sources, read documents, and organize evidence.
View stack →03Customer Support
Find customer context, consult knowledge, and prepare responses.
View stack →04Backend & APIs
Explore APIs, inspect application data, and investigate service errors.
View stack →05Data Analysis
Query datasets, explore spreadsheets, and communicate findings.
View stack →06DevOps
Inspect infrastructure, follow deployments, and understand system health.
View stack →07QA & Testing
Check user journeys, exercise APIs, and track reproducible defects.
View stack →08Technical Writing
Read source material, check references, and maintain clear documentation.
View stack →09Product Management
Connect customer context, product decisions, and delivery work.
View stack →10SEO & Content
Research topics, inspect pages, and ground content decisions in evidence.
View stack →11Design & Accessibility
Bring design context into implementation and review the rendered experience.
View stack →12Security Review
Review your code, inspect dependency risks, and document remediation work.
View stack →Build my stack
Your stack / Cursor
Research
3 selected
Source discovery
Find sources relevant to your research.
Search the Web for pages, images, news, videos, and more using the Brave Search API.
7 alternatives
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Visit https://brave.com/search/api/ for a free API key. Search the web, local businesses, images,…
Exa MCP for web search and web crawling!
Exa MCP for web search and web crawling!
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.
🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
Reading and extraction
Retrieve source material for closer reading.
MCP server for loading and extracting text from PDF files with chunked pagination and interactive viewer
7 alternatives
Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.
Fetches a URL from the internet and extracts its contents as markdown
A flexible HTTP fetching Model Context Protocol server.
MCP server for web fetching with Cloudflare bypass, Trafilatura extraction, and smart routing. Free, self-hosted, no API keys.
📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test coverage
Production ready MCP server with real-time search, extract, map & crawl.
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.
Research notes
Keep findings with your research notes.
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
7 alternatives
Official MCP server for Notion API
Tasks that outlive the chat. Capture features and tasks on your phone; your AI agent picks them up.
Notion Skills + Notion MCP server packaged as a Cursor plugin
A Model Context Protocol server for connecting Notion to MCP-compatible clients
MCP server that interacts with Obsidian via the Obsidian rest API community plugin
Research skill
Apply a repeatable approach to evidence and synthesis.
No matching entry in the current catalog results. Browse the directory