Web Scraping & Data Collection MCP Servers

Weather

Provides weather information, including alerts and forecasts, using the National Weather Service API.

Ez Web Search

Performs web searches using DuckDuckGo and returns a list of results, formatted for use within an MCP client.

TryKitt.ai

Enables AI assistants to find and verify B2B email addresses using the TryKitt.ai API.

F1 Data

Provides Formula 1 data access through various APIs for integration with large language models.

MVG Störung

Provides cached access to Munich Public Transport (MVG) disruption data.

Google Search

Provides web search capabilities using Google Custom Search API and extracts content from webpages for AI model integration.

Model Context Python

Provides a server implementation for the Model Context Protocol, enabling searching and extracting information from arXiv scientific papers.

ITIS

Accesses the Integrated Taxonomic Information System (ITIS) database to retrieve taxonomic data via its SOLR API.

Yahoo Finance

Provides comprehensive financial data, including real-time market information, historical prices, and economic indicators from Yahoo Finance.

LitSynth

Facilitates intelligent academic paper discovery and semantic search on ArXiv using state-of-the-art sentence transformers.

DNSDumpster

Enables AI assistants to perform detailed DNS reconnaissance by querying the DNSDumpster API.

DuckDuckGo

Integrates DuckDuckGo search, analysis prompts, and region resources into Model Context Protocol (MCP) clients and provides a dedicated command-line interface.

PubChem

Automatically retrieves toxicology, GHS safety classification, and chemical property information from compound names or CIDs using the PubChem REST API.

User Data Enrichment

Enriches user profiles by finding and returning social media links from public sources based on name and birth date.

FPL

Accesses Fantasy Premier League (FPL) data and provides a suite of tools for player, team, and gameweek information.

SearXNG

Facilitates multi-query web searches and dynamic page scraping, optimizing results for LLMs using TOON encoding.

ScrapeBadger

Enables AI agents to access comprehensive Twitter/X data, including user profiles, tweets, trends, and communities, via the Model Context Protocol.

Web Search

Access Google search and extract web page content through a unified Model Context Protocol server.

Crypto

Accesses real-time and historical cryptocurrency market data, providing tools for live pricing, candlestick data, and streaming updates.

Social Intel

Enables comprehensive Instagram influencer searches based on diverse criteria, operating on a pay-per-request model.