"A website for discovering new pump.fun launches" matching MCP servers:

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables querying New Caledonia public open datasets from data.gouv.nc across 10 domains and 29 tools, including holidays, companies, employment, weather, mining, environment, population, tourism, and transport, via stdio for MCP clients.

Provides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.

Finds new AI model, product and repository names on X, Hugging Face, GitHub and sitemaps, plus sites that just added a payment link, then sizes their keywords with search volume, Google Trends and page-one competition.

A local RAG MCP server that indexes project documentation and code into ChromaDB for semantic search, supporting multiple tech stacks and deployment modes.

Convert PDF, DOCX, XLSX, images, and 20+ formats to Markdown using markdown.new API.

Enables AI assistants to interact with the Pump.fun platform on Solana for creating, buying, and selling meme tokens. Provides comprehensive token management including balance checking, account management, and secure transaction handling.

A Model Context Protocol server enabling AI assistants to create, buy, and sell tokens on the Pump.fun platform on Solana.

An MCP server for automated website generation that transforms Excel spreadsheets and structured data into responsive portfolios, catalogs, and directories. It enables users to create complete websites, add pages, and generate components through natural language and template-based integration.

A Model Context Protocol server that saves prompts with timestamps and allows users to list previously saved prompts for Claude Desktop.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Local MCP server for A-share stock trading via Tonghuashun, offering account/position queries, buy/sell/cancel orders with risk controls and forced user confirmation; currently simulated with a reserved interface for real broker channels.

Captures high-quality screenshots of web pages with automatic resolution limiting and tiling optimized for Claude Vision API and other AI models.

An MCP server for searching and downloading books from Library Genesis, supporting EPUB, MOBI, PDF, and more through natural language queries.

An MCP server providing comprehensive HubSpot CMS development documentation, enabling users to get contextual information about building HubSpot websites through natural language.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

MCP server that launches Mesen/MesenCE headlessly and exposes the emulator's debugger-face Lua API over MCP JSON-RPC, enabling AI agents to load ROMs, step frames, inspect memory/registers, manage breakpoints/watches, trace execution, and export Code/Data Logger maps for SNES, NES, PC Engine, and Game Boy Advance.

Fetches webpages and converts them into clean Markdown for token-efficient scraping by AI agents, preserving links and supporting configurable multi-page crawling, caching, and robots.txt-aware rate limiting.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables MCP clients to capture web page and DOM element images, tile full pages into AI-friendly chunks, and record animated screencasts with configurable waits and JavaScript injection.

Captures high-quality webpage screenshots optimized for AI vision workflows, automatically tiling full pages into 1072x1072 chunks, with support for element-specific captures, configurable waits, and screencasts.

Enables capturing fast, always-fresh webpage screenshots via Puppeteer, automatically tiling full pages into 1072x1072 chunks sized for AI vision models. Also supports CSS-selector element capture, customizable viewports and wait strategies, and timed screencasts exportable as animated WebP.

Enables AI agents to fetch webpages locally, extract main content, and convert it into clean, token-efficient Markdown with preserved links. Supports configurable multi-page crawling, caching, robots.txt compliance, and optional chunking for downstream processing.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Fetches web pages, strips noise, and converts them to clean Markdown with preserved links and optional multi-page crawling, enabling token-efficient web content extraction for AI agents and LLM pipelines.

Enables AI agents and LLM pipelines to fetch and crawl webpages, strip extraneous content, and convert them into clean, link-preserving Markdown for fast, token-efficient scraping.

Enables AI agents to fetch and crawl websites locally, extract main content, preserve links, and convert pages to clean Markdown with minimal token footprint.

Enables AI coding and vision tools to capture fresh webpage screenshots, automatically tile full pages into 1072x1072 chunks, capture CSS-selected elements, and record screencasts as PNG or animated WebP files.

Fetches webpages and converts them into clean, token-efficient Markdown, optionally crawling multiple linked pages while respecting robots.txt and caching results for AI agents and LLM pipelines.