Browse the catalog

A hosted Model Context Protocol server providing read-only YouTube tools for search, video/channel data, and transcripts, with no Google Cloud project or API key required.

Enables 大六壬 divination by computing the chart (三傳, 四課, etc.) and generating a 天地盤 PNG from a given datetime.

iOS Simulator MCP Tool provides a bridge between Claude and iOS simulators, enabling interaction with virtual iOS devices through a set of specialized tools. Built by Joshua Yoes, it leverages Facebook's IDB tool to allow users to get information about simulators, control UI interactions (tapping, swiping, typing), and inspect UI elements on screen. The implementation is packaged as an NPM module that can be easily integrated with Cursor via MCP configuration, making it valuable for developers who need to test, debug, or demonstrate iOS applications without manually operating the simulator.

MCP server for securely connecting LLMs to customer data, providing customer profile retrieval, semantic search of interaction history, and exact financial summaries via SQL aggregation, with audit logging and prompt injection protection.

Local daemon that bridges AI assistants to the local filesystem with read-only commands and optional write mode, enforcing strict security filters to prevent credential leakage.

Multi-agent orchestration plugin for Claude Code + cross-project graph-memory MCP server

An MCP server that provides technical consultation, code review, and code explanation by integrating with OpenAI's Codex CLI, enabling AI-powered coding assistance in a sandboxed, read-only environment.

Zillow property data for AI agents — search listings by city or ZIP, look up any US address, and get 50+ fields per property including prices, Zestimates, price history, and sold data.

A Python-based MCP server built by ackness that provides HTTP data fetching and JSON extraction capabilities using JSONPath patterns. The implementation offers four core tools: single and batch JSON extraction from URLs with configurable JSONPath filtering, and single and batch raw text content retrieval, all with concurrent processing for improved performance. Features comprehensive HTTP client configuration through environment variables including custom headers, proxy support, SSL verification controls, and timeout settings, along with robust error handling and validation using Pydantic models. Designed for AI assistants that need to programmatically fetch and parse structured data from web APIs or extract specific fields from JSON responses at scale.

This MCP server provides comprehensive access to fal.ai's AI model ecosystem, enabling AI assistants to discover, execute, and manage generative AI workflows through a unified interface. Built using Python with FastMCP, httpx for async HTTP operations, and support for both direct and queued model execution, it offers tools for browsing available models with pagination and search, retrieving OpenAPI schemas for model parameters, generating content with any fal.ai model including image generation and other AI tasks, and managing long-running requests through queue operations with status checking and cancellation. The implementation includes file upload capabilities to fal.ai's CDN storage, full streaming support via HTTP transport for real-time communication, and handles both authenticated operations requiring API keys and public model discovery, making it valuable for AI assistants that need access to cutting-edge generative models, automated content creation workflows, and scenarios requiring integration with fal.ai's specialized AI model marketplace.

Provides access to real-time and historical snow conditions, weather data, and snowpack analysis from over 800 SNOTEL stations across the western United States through the USDA Air and Water Database API.

Provides a clean interface for AI agents to search arXiv papers, fetch metadata, read full text, and download PDFs/source, with rate-limiting, on-disk caching, and session pinning to avoid duplicate fetches.

Turns a CSV — or a public dataset named in plain English — into an animated chart video. Every numeric claim in the generated narration is recomputed from the source rows before export, and a claim that does not reconcile blocks the export rather than shipping.

Provides as-reported US equity fundamentals, live quotes, financial statements, valuation comps, and a screener from SEC filings, with per-cell filing provenance for citations.

Enables dice rolling mechanics for tabletop RPGs including standard dice notation, coin flips, advantage/disadvantage rolls, exploding dice, and maintains a history of recent rolls. Supports D\&D 5e mechanics and various gaming dice types (d4, d6, d8, d10, d12, d20, d100).

Queries traffic metrics, conversions, and time-period comparisons from Plausible Analytics. Retrieves visitor counts, pageviews, bounce rates, conversion rates, and breakdowns by page, source, country, device, browser, and UTM parameters. Supports both Plausible Cloud and self-hosted instances.

Acts as a stdio-to-HTTP proxy for the 1C runtime-MCP service, enabling MCP clients like Claude Desktop to interact with 1C tools.

A Model Context Protocol server that provides Flutter UI templates for development. It enables users to access and integrate pre-built Flutter UI components through MCP-compatible client applications.

An MCP server that enables managing Docker containers through natural language commands, allowing users to create, list, and delete containers. It facilitates automated container orchestration and integrates with VS Code via the Cline extension.

Multi-agent LangGraph deep research workflow that identifies emerging challenger brands competing with P&G products and explains why consumers like them.