"Information about ghosts or paranormal phenomena" matching MCP servers:

An MCP (Model Context Protocol) server that gives AI agents live, structured ad intelligence across Facebook, Google, and Instagram — data that no base model can produce from training alone. Powered by Apify actors. Works with any MCP-compatible client: Cursor, Claude, etc.

Provides live wait times and office details for all 60 Oregon DMV field offices by scraping the ODOT website, with no authentication required.

Self-hosted MCP toolkit providing web search, Wikipedia, and arXiv access without mandatory API keys, delivered as a Docker Compose bundle.

Enables users to retrieve and structure shipment tracking information from DB Schenker's website using natural language queries.

Lets an MCP client read allowlisted pages from the LiveSwapFace website, retrieve its official links, and estimate credits for a planned browser session using rates fetched at call time. It is read-only and never performs face swaps, signs in, uploads media, or touches a private API.

Extracts people (names and titles) from a company's team, leadership, or about page given a domain. Uses Apify to crawl and return structured data, with optional filters for seniority and email inclusion.

Enables MCP clients to search by name plus company information and receive candidate LinkedIn profile links with confidence scores, headline/follower details, and current-or-former employer flags without accessing LinkedIn directly.

Search public Japanese articles about mamakatsu on Mama Rich. Returns article titles, descriptions, and source URLs. No API key required.

Enables AI agents to retrieve live product prices, stock, variants, and deal ratings from Shopify, WooCommerce, Walmart, eBay, and Amazon by pasting product links and asking about price, availability, or comparisons.

LinkedIn prospect intelligence inside Claude. It automates the research behind outreach, not the sending: scrapes posts, profiles and comment threads into a local SQLite database, classifies what a person or company actually posts about, mines comment threads for people already describing your problem, and surfaces uncommon commonalities worth opening with.

Enables LLM agents to query live Citilink product data with accurate city-specific prices, ratings, reviews, stores, and markdown units, while filtering out misleading or implausible information.

Crawls Korean stock market data from Naver Finance, providing real-time information on top searched stocks and detailed stock information by stock code.

Fetches web pages, converts HTML to markdown, and uses Claude to answer questions about the content.

Enables web content extraction, screenshot capture, web search, arXiv paper search, and image search through Jina AI's APIs. Provides tools for reading URLs as markdown, searching the web for current information, and finding academic papers or images.

Provides AI-powered web search, full-page content extraction, and search-enhanced Q\&A capabilities via the Metaso AI search engine. It enables large language models to access diverse information across web, academic, and multimedia sources with structured Markdown or JSON output.

A Model Context Protocol (MCP) server that provides tools for searching and fetching information from Hacker News.

Search for Airbnb listings and get detailed information about specific properties. Effortlessly plan your next trip with structured data and no API key required, while respecting Airbnb's guidelines.

Enables agents to crawl and read websites politely, learning per host which reader, URL rewrite, or detail path actually reaches good information, and reusing those wins across runs or a shared database. Failures come back as coded errors with concrete next steps, so blocked or empty pages point to an honest alternative instead of endless retries.

Enables querying clinical trial information from the Chinese Clinical Trial Registry (ChiCTR) by searching trials with keywords, registration numbers, or years, and retrieving detailed trial information.

Enables searching for Airbnb listings and retrieving detailed accommodation information with direct links to Airbnb pages.

Enables LLMs to autonomously retrieve and explore web content by fetching pages and recursively following links to a specified depth, particularly useful for learning about topics from documentation.

Enables scraping and comparing pricing information for LLM inference services across multiple providers (CloudRift, DeepInfra, Fireworks, Groq) using Firecrawl API and SQLite storage.

Enables users to stream or download YouTube video information and direct links via the Ytstream API. It supports geographic optimization and language selection for better download speeds and audio availability.

Provides AI coding agents with a live web search tool that returns extracted, answer-ready text from web pages. Enables real-time information retrieval without any local installation or maintenance.

Enables AI assistants to query BuiltWith's technology detection data directly, supporting natural language questions about website technologies.

Drive Clearcote, a Chromium build with its fingerprint protection patched into the engine, from any MCP client: about 20 tools to navigate, read, extract, click, fill, screenshot and keep sessions, plus a CDP endpoint that hands the same browser to Playwright or Puppeteer. The server lives in the repo's mcp/ folder (npx clearcote-mcp or pip install clearcote-mcp).

Atlas helps AI agents understand and use information from the web without token bloat or hallucinations. It transforms messy web pages, SPAs, and documentation into clean, structured Markdown and JSON, providing powerful tools for deep compilation, fast scraping, multi-page crawling, and domain mapping.

Enables AI assistants to retrieve product information and run a robots.txt check through remote MCP tools.

Enables LLMs to research answers using DuckDuckGo web and news search plus Wikipedia, providing up-to-date information and current events.

Enables querying Chinese MIIT ICP filing information by domain, organization, or app name, with support for websites, mobile apps, mini-programs, and quick apps via HTTP or stdio.