Web Scraping & Data Collection MCP 서버

Divslingerx

Enables web search functionality via Google using a lightweight and stateless Model Context Protocol (MCP) server.

Website Fetcher

Retrieves raw website content through a lightweight API endpoint, serving as an MCP server demonstration.

YT Transcript

Fetch and analyze YouTube video transcripts for detailed content insights, bypassing rate limits with CLI-based yt-dlp.

NHL

Provides live NHL data and statistics with natural language query capabilities through an MCP server.

OECD

Provides AI assistants and chatbots with access to OECD's comprehensive statistical data through its SDMX API.

Government of Canada Data

Accesses Canada's Open Government data for comprehensive dataset discovery and provides specialized querying for national transportation infrastructure information.

SciTeX Dataset

Unifies access to neuroscience datasets, enabling discovery and fetching of metadata from major repositories like OpenNeuro, DANDI, and PhysioNet through a single Python API and CLI.

Signal Relay

Connects AI agents to SocioLogic's synthetic persona platform via the Model Context Protocol.

OpenAlex

Provides AI agents with structured tools to search and retrieve academic articles, authors, and institutions from the OpenAlex scholarly database.

Go Enriche

Enriches web content by fetching pages, extracting article text, parsing structured data, and providing context search capabilities.

Agent Commerce Core

Normalizes unstructured web data for AI agents, performing semantic extraction, HTML parsing, and generating structured RAG output.

Gelbooru

Accesses Gelbooru data to generate Stable Diffusion prompts and explore character appearance and art via the Model Context Protocol (MCP).

Korean Data

Provides AI assistants with direct access to live Korean web data from platforms such as Naver, Melon, Daangn, Bunjang, and Musinsa via Apify actors.

Stealth Fetch

Fetches and parses web content with browser-grade TLS fingerprint impersonation for resilient web data extraction.

Readdown

Converts web pages to clean, LLM-optimized Markdown without needing a browser.

Browser

Automate web browsing actions including navigation, clicking, typing, and capturing screenshots through Playwright.

ESPN

Delivers real-time ESPN sports data directly to AI assistants, offering 12 specialized tools for live scores, standings, and athlete statistics across 25+ leagues.

Hacker News

Provides standardized access to Hacker News feeds, threaded discussions, user profiles, and full-text search.

InsuranceOracle

Provides comprehensive insurance intelligence through 12 specialized tools covering products, tariffs, claims, and risk assessment.

MovieOracle

Provides comprehensive film and entertainment intelligence, offering access to search, trending content, and ratings from major platforms.