Browse the catalog

Pipeworx install kit for Perplexity custom MCP connector — 6,000+ live data tools across 1,600+ sources.

This TMDB MCP server provides integration with The Movie Database API for accessing movie, TV show, and entertainment industry data through ten specialized tools including search functionality, detailed information retrieval, trending content discovery, and people lookup capabilities. Built with TypeScript using Express and Axios, it features dual deployment modes with both standard MCP protocol support via stdin/stdout communication and HTTP server mode for web-based integrations, plus Docker containerization and comprehensive error handling for TMDB API responses. The implementation automatically constructs image URLs for posters and backdrops, supports pagination and advanced query parameters like year filtering and additional data appending, and includes legacy tool discovery for backward compatibility, making it valuable for AI assistants building entertainment recommendation systems, movie databases, or content discovery applications.

Provides semantic search and intelligent access to SAP AI Core documentation for AI assistants like Claude. It enables users to search across categories, retrieve full document content, and access topic-specific information from the SAP artificial intelligence repository.

Architecting a Secure, Multi-Agent GenAI Support System

511 SF Bay Transit MCP — live departures, vehicle positions and service

Pile in. Sort out. Taskpile is an AI-first productivity task manager that lives inside your chat client — capture in Claude, plan in ChatGPT, finish in the app. 57 tools cover task CRUD, projects, tags, teams, bulk ops, and a morning digest.

Provides an OCR tool that extracts text from images using macOS's built-in Vision framework, returning text segments with confidence scores and bounding boxes.

Helps users choose which Steam games to play or buy by analyzing their library, playtime, discounts, and reviews.

An MCP server that enables interaction with local camera devices to capture and process images. It allows LLMs to access video devices with configurable settings such as resolution, orientation, and image format.

An MCP server that connects AI assistants to SEO platforms like Google Search Console, GA4, Bing Webmaster Tools, and Adobe Analytics, enabling natural language queries about SEO performance.

The official Sketch MCP Server

Provides access to Ukraine's Prozorro government procurement system, enabling queries against public tender data. The server integrates with the Prozorro API to search tenders by procuring entity EDRPOU codes, legal names, and date ranges, returning structured procurement information including tender details, amounts, and participating organizations. Built for transparency and procurement analysis use cases, it helps track government spending, identify business opportunities, and monitor public sector procurement activities across Ukrainian government agencies.

The best PTT MCP server

This MCP server provides automated causal inference capabilities by combining LLM-guided variable classification with DoWhy statistical analysis on SQLite banking data. Built with Python using FastMCP, LangGraph, and OpenAI's GPT-3.5-turbo, it features a single tool that takes treatment and outcome variables, uses AI to classify other variables as confounders, mediators, effect modifiers, colliders, or instruments, generates causal graphs in DOT format, and executes DoWhy code to estimate Average Treatment Effects using backdoor adjustment with linear regression. The implementation includes both standalone agent and MCP server versions, automatically generates plain-language business summaries of causal effects, and works with predefined banking variables like customer demographics, engagement metrics, and Internet Banking activation, making it valuable for business analysts exploring causal relationships in customer data without requiring deep statistical expertise.

DappQL Core Packages

This MCP server, developed by Kirill Markin, provides a simple tool for fetching website content. Built with Python and leveraging the MCP library, it offers a standardized interface for AI models to retrieve web page data. The implementation focuses on ease of deployment, with Docker and Heroku support, and includes configuration options for customizing server behavior. By enabling AI assistants to access web content through a unified API, this server facilitates use cases such as web scraping, content analysis, and information retrieval. It's particularly useful for applications and AI models that require programmatic access to web data without dealing with the complexities of direct HTTP requests and HTML parsing.

Publish live web pages from AI coding agents. Instant shareable URLs for dashboards, landing pages, and reports with password protection.

Film stills from 5,489 films, searchable by lighting, lens character, shot size, colour and mood.

Provides TikTok hashtag trend data including volume growth, viral spikes, and historical time series, enabling AI assistants to spot emerging trends before they go mainstream.

Headless MCP server for Eclipse MAT that enables analyzing Java heap dumps using built-in commands, OQL queries, and predefined reports.