Browse the catalog

Meteoswiss Open Data Tools for LLMs - MCP server and Agent Skill

This MCP server provides a streamlined interface to the Sketchfab API, enabling users to search for and download 3D models. Developed by Eduardo del Palacio Lirola, it exposes two primary tools: one for searching downloadable models with filtering options for animated or rigged content, and another for downloading models by their unique identifier. The implementation is containerized with Docker for easy deployment and requires a Sketchfab API token for authentication, making it ideal for applications that need programmatic access to Sketchfab's extensive 3D model library.

An MCP server that wraps the UTEL IP-telephony REST API as MCP tools, enabling LLM agents to make authenticated HTTP requests to the UTEL API via a simple tool interface.

YepCode MCP Server enables AI platforms to interact with YepCode's infrastructure, allowing them to run LLM-generated scripts and use YepCode processes as AI tools. It provides secure code execution in isolated environments, environment variable management, and process execution capabilities through a standardized MCP interface. The server supports both local and remote integration options with AI platforms like Cursor and Claude Desktop, making it ideal for teams that need to execute code or automate workflows directly from AI assistants while maintaining enterprise-grade security.

Integrates with Lemon Squeezy to manage subscriptions, checkouts, products, orders, customers, license keys, and webhooks programmatically with audit logging capabilities.

Multi-provider embedding MCP server with local Milvus for semantic code search. Works with Claude Code, Cursor, Windsurf, and other MCP-compatible IDEs.

Enables access to news from multiple sources including Google News and DuckDuckGo, supporting queries by location, category, site, date range, and providing top news headlines with detailed information.

A TypeScript-based MCP server for interacting with Apple Calendars on macOS, providing a standardized interface for AI models to read, create, update, and delete calendar events. Built to work with a companion Swift-based Calendar API Bridge, the implementation supports flexible date parsing and handles calendar permissions through a local HTTP server running on port 8080. Particularly useful for AI assistants that need to manage scheduling or retrieve calendar information directly from a user's macOS system.

MCP server for ADALM2000 (M2k) — AWG, scope, and PSU control via FastMCP 3.4.

紫微AI，是一个紫微斗数解盘AI应用。Ziwei AI is an AI application for Ziwei Doushu chart interpretation.紫微AIは、紫微斗数のチャート解読のためのAIアプリケーションです。

Enables AI models to manage workflows, credentials, nodes, templates, and monitor executions on the n8n automation platform through a standardized MCP interface.

MCP server for birding trip planning with migration forecasts, hotspot analysis, and daily email briefings, integrating eBird, BirdCast, NWS, and iNaturalist data.

Shared MCP HTTP server infrastructure for plugin projects, providing Express + Streamable HTTP transport, OAuth/OIDC auth, runtime configuration, tool registration, and widget support.

Provides virtual Visa card issuance for AI agent workflows through the PayClaw platform. Create just-in-time cards with spending limits, require human approval for transactions, and manage card lifecycle. Designed for MCP-native payment flows where AI agents need to make purchases with built-in safety controls.

Enables users to fetch random jokes from the API Ninjas Jokes API. Supports retrieving 1-30 jokes per request through a simple interface.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

A local, MCP-powered utility that transforms messy text into structured notes using your custom templates and prompts. By leveraging LLMs for intelligent formatting, it securely routes content to your vault while keeping you in full control of file paths and organization.

Zero-dependency React component library with 147 components, 3 weight tiers (Lite/Standard/Premium), physics-based animations, OKLCH color system, Aurora Fluid design, and built-in MCP server for AI assistants

Enables AI assistants to run Godot unit tests using GUT and read results in a structured format

Provides non-custodial, post-quantum encrypted memory for AI agents, enabling portable memory across models with provable erasure.