Packages

An MCP server wrapping yt-dlp that enables AI agents to search YouTube, download videos/audio, extract metadata, and retrieve transcripts via natural language commands.

C# Runner MCP server enabling AI agents to execute C# code snippets — running C# scripts via dotnet-script or similar runtime, capturing console output and return values, and integrating C# code execution into agent-driven .NET development, testing, and automation workflows.

DataForSEO MCP server enabling AI agents to access comprehensive SEO and search data — fetching SERP results for any keyword, retrieving keyword metrics (search volume, CPC, competition), analyzing backlinks, and integrating DataForSEO's professional SEO data API into agent-driven SEO analysis and digital marketing workflows.

MCP server for comparing two JSON files deeply without worrying about key or array order. Detects structural differences, missing fields, and value changes between JSON structures — enabling AI agents to identify what changed between JSON configurations, API responses, or data files.

Jupyter MCP server enabling AI agents to interact with Jupyter notebooks and kernels — executing code cells, reading notebook content, creating and modifying notebooks, managing Jupyter kernels, and integrating Jupyter's interactive computing environment into agent-driven data science and research workflows.

Next.js MCP server enabling AI agents to assist with Next.js development — generating App Router pages and components, creating API routes, scaffolding Next.js project structures, providing Next.js 14/15 App Router documentation, server actions, and metadata API reference, and integrating Next.js-specific patterns into agent-driven React web development workflows.

Svelte 5 MCP server enabling AI agents to assist with Svelte 5 development — generating Svelte 5 components with runes syntax, providing Svelte 5 documentation and API reference, scaffolding SvelteKit routes and layouts, and integrating Svelte 5's new runes-based reactivity model into agent-driven frontend development workflows.

AWS Lambda MCP server enabling AI agents to invoke and manage AWS Lambda functions — calling Lambda functions with payloads, listing available functions, inspecting function configurations, and integrating AWS Lambda's serverless compute capabilities into agent-driven automation, event processing, and cloud orchestration workflows.

Multi-carrier shipping API that normalizes label creation, rate shopping, address verification, and tracking across 100+ carriers (UPS, USPS, FedEx, DHL, etc.) through a single unified interface.

Official Fly.io MCP server enabling AI agents to interact with Fly.io's distributed application platform — deploying and scaling Fly apps, managing Machines, querying app status, and operating globally distributed services.

Gemini MCP server by Philipp Schmid (Hugging Face developer advocate) enabling AI agents to use Google's Gemini language models — generating text, analyzing images, processing documents, and integrating Gemini's multimodal capabilities into agent workflows. Provides access to Gemini Pro and Gemini Flash models through a standard MCP interface.

Human-in-the-Loop MCP server enabling AI agents to request human approval or input before taking actions — pausing agent workflows for human review, collecting human decisions and confirmations, and integrating human oversight checkpoints into agent-driven automation workflows requiring approval gates.

Official Kestra MCP server enabling AI agents to interact with Kestra's workflow orchestration platform — triggering flows, monitoring executions, managing namespaces, and integrating data pipeline workflows into agent-driven automation.

PocketBase MCP server enabling AI agents to interact with PocketBase — the popular single-file open-source backend (BaaS) built with Go and SQLite. Enables querying and modifying collections, managing records, handling file attachments, managing authentication, and integrating PocketBase's real-time database and API into agent workflows for rapid application development and data management.

Redis MCP server enabling AI agents to interact with Redis in-memory data store — getting and setting key-value pairs, working with Redis data structures (lists, sets, hashes, sorted sets), executing Redis commands, inspecting TTLs and expiry, and integrating Redis's fast in-memory capabilities into agent-driven caching, session management, and real-time data workflows.

MCP server providing ephemeral data sandboxes for AI workflows with built-in guardrails and security controls. Enables agents to create temporary data stores for workflow state, intermediate results, and scratchpad operations — with automatic cleanup and security boundaries to prevent agents from persisting sensitive data unintentionally.

Lightweight MCP server implementation for constrained embedded devices by Golioth — the cloud platform for embedded IoT. TinyMCP brings the Model Context Protocol to microcontrollers and RTOS environments (Zephyr, FreeRTOS), enabling edge AI agents to interact with embedded firmware, sensor data, and device controls through MCP-compatible interfaces.

Trello MCP server enabling AI agents to interact with Trello's kanban-style project management platform — managing boards, lists, cards, labels, and checklists; querying card status; creating and updating work items; and integrating Trello's visual project tracking into agent-driven task management workflows.

An MCP server and Claude Code plugin that enables natural voice conversations with Claude Code and other MCP-capable AI agents, supporting both cloud (OpenAI) and fully local (Whisper + Kokoro) speech processing with smart silence detection.

Yokai is a simple, modular Go backend framework that provides built-in dependency injection, logging, tracing, metrics, health checks, and support for HTTP, gRPC, MCP server, and worker application patterns with minimal boilerplate.