Web Scraping & Data Collection Servidores MCP

Brightspace

Connects Purdue students' Brightspace accounts to access academic data via web scraping, handling Duo Mobile 2FA.

Paperscraper

Scrape publication metadata from PubMed, arXiv, medRxiv, bioRxiv, and ChemRxiv.

Bible

Provides AI assistants and applications with robust access to Bible passages from various translations via a Model Context Protocol server.

Gremlin Web Scraper

Scrapes and crawls visible text content from public web pages using a lightweight HTTP module designed for the VS Code Model Context Protocol.

PDF Reader

Provides server-based capabilities for extracting text, recognizing OCR content, and extracting images from PDF documents.

Web Tools

Enables Large Language Models to interact with web content through standardized tools.

OSRS

Enables programmatic access to Old School RuneScape (OSRS) Wiki content and core game data definitions.

OpenFEC

Provides access to Federal Election Commission campaign finance data through the OpenFEC API using the Model Context Protocol.

DuckDuckGo Search Integration

Provides an MCP server to enable AI systems to perform various types of searches using the DuckDuckGo search engine.

News Instagram

Automates the intelligent scraping, AI-processing, and publishing of Canadian news into engaging Instagram content.

Webcrawl

Connects web crawler data and archives to AI language models using the Model Context Protocol.

GeoGuessr

Analyzes GeoGuessr game statistics, offering multi-user support, automatic API monitoring, and dynamic schema adaptation for data retrieval.

MOEX

Provides an MCP server interface to selected MOEX Information and Statistical Server (ISS) endpoints.

Google Search

Provides Google Custom Search functionality as a Model Context Protocol (MCP) server.

LangGraph Financial Agent

Integrates Model Context Protocol with LangGraph to build an intelligent ReAct agent capable of accessing real-time financial data.

SynapseFlow

Automates academic research and hypothesis generation with a self-learning multi-agent system, processing thousands of papers per minute and visualizing real-time citation graphs.

YetiBrowser

Empowers Model Context Protocol clients to automate real browser tabs securely and locally using Node.js and dedicated browser extensions.

Schwaizer BFS

Provides programmatic access to statistical data from the Swiss Federal Statistical Office (BFS) through the Model Context Protocol (MCP).

Mcp Servers

Extends AI assistants with secure access to local files, Gmail, and web content via Model Context Protocol (MCP).

Web Search

Performs advanced web searches across multiple engines and extracts text content from web pages.