Browse the catalog

Provides real-time weather alerts from the National Weather Service API via the Model Context Protocol. It allows LLMs to fetch active alerts for specific US states using both STDIO and SSE transport protocols.

FFmpeg-MCP provides a server implementation that enables AI assistants to perform video manipulation tasks through natural language commands. Built around the FFmpeg command line tool, it offers functionality for searching video files, retrieving video metadata, cutting clips, concatenating videos, and controlling playback. The server currently supports macOS platforms (both ARM64 and x86_64) and is designed for use cases where AI assistants need to help users with video editing and management tasks without requiring direct interaction with command line tools.

Enables Claude Code to control a browser via Playwright for web scraping, automation, and research, with features like navigation, screenshots, form filling, and PDF export.

Connects Memlane, your personal library of saved links and notes, to AI assistants via MCP. Enables semantic search, browsing, saving URLs, and managing notes and topics.

AI-synthesized 3-bullet DeFi risk dossier for any Base wallet. Pre-trade counterparty vetting for MEV and arbitrage bots via x402 ($0.10 USDC per query).

MCP server for Japanese business days, public holidays, wareki dates, and tax arithmetic, helping AI agents avoid common Japanese date and tax errors.

Decompiler for compiled iOS/macOS interface files (.nib, .storyboardc): object tree, wiring, custom classes, navigation graphs

DuckDuckGo-powered web search and content extraction server that performs research by searching the web, fetching full page content, and extracting clean text from HTML. Built with a modular pipeline architecture featuring configurable filtering, caching, concurrent fetching, and multiple output formats (JSON, markdown, raw text), it provides tools for both quick searches and comprehensive research workflows. Includes smart content filtering to avoid low-quality pages, automatic text extraction and cleaning, built-in rate limiting, and runtime-configurable domain blocklists.

Enables AI agents to generate images and videos via the Corent API with automatic model routing, provider fallback, and tools for planning, creation, and balance management.

Provides cognitive bias management capabilities for AI agents, allowing configuration and application of various cognitive biases to influence reasoning patterns. Includes preset bias profiles for different personas and supports dynamic bias adjustment through get, set, remove, and reset operations.

A privacy-friendly web search MCP server using SearXNG, enabling searches across multiple engines and categories.

This MCP server provides temporary email management through integration with the ChatTempMail API, built by Selenium39 for handling disposable email addresses programmatically. The implementation offers tools for creating temporary email addresses, retrieving messages, and managing email sessions without requiring permanent email accounts, featuring configurable API endpoints and secure API key authentication through environment variables. Designed for developers, testers, and automation workflows that need temporary email functionality for account verification, testing email flows, or protecting privacy during online registrations where disposable email addresses are required.

MCP server that renders diagram-as-code to PNG or text art, locally. No browser, no network.

Enables classification of galaxy images by Hubble type and answering custom astronomy questions using the Qwen VL vision-language model via DashScope.

An MCP server for HPE Juniper Security Director Cloud that exposes 368 tools to manage firewall policies, NAT policies, security resources, and more via the full OpenAPI surface. Enables LLMs to directly interact with and configure a live Security Director Cloud environment.

A Model Context Protocol (MCP) server that allows Claude AI to interact with custom tools, enabling extension of Claude's capabilities through the MCP framework.

This LiteLLM MCP server integrates the LiteLLM library to provide a standardized interface for AI assistants to interact with OpenAI language models. Built using Python and leveraging libraries like Pydantic and FastAPI, it abstracts the complexities of the OpenAI API, handling authentication, request formatting, and response parsing. The server offers text completion capabilities with customizable parameters, enabling AI systems to generate human-like text across various applications. It's designed for developers and researchers who need flexible access to state-of-the-art language models, facilitating use cases such as chatbots, content generation, and natural language processing tasks. The implementation's focus on LiteLLM allows for potential future expansion to support additional model providers beyond OpenAI.

Enables uploading images and files to Notion pages from Cursor chat, supporting multiple attachment types like image blocks, file blocks, cover images, and icons.

Bridges the full Zabbix API surface to MCP, automatically mapping every Zabbix namespace and method (e.g., host.get, trigger.create) into individual callable tools. Supports both token-based and username/password authentication against any Zabbix instance. Useful for querying hosts, problems, triggers, events, and metrics, as well as managing templates, users, and maintenance windows.

An API that exposes Unsplash image search, listing, and random photo capabilities as MCP tools, enabling AI models like Claude to directly interact with Unsplash's services.