Packages

<!-- mcp-name: io.github.mhajder/zabbix-mcp -->

Zapier's API for triggering, managing, and integrating with Zapier's no-code workflow automation platform, enabling 7000+ app integrations through webhooks and REST hooks.

Modern Zig AI development assistant - optimized for Zig 0.15.2+ with comprehensive build system support

> The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.


<div align="center">

Self-hosted zero-knowledge expiring secrets. Encrypt locally, store ciphertext on the server, share a URL with the decryption key in the fragment. The server never sees the plaintext or the key.

<!-- mcp-name: io.github.ariroffe72/zmanim-mcp-server -->

dav-mcp provides an MCP server (and optionally an HTTP interface) that exposes CalDAV (calendar), CardDAV (contacts), and VTODO/VTODO-over-CalDAV-style (tasks) operations as a set of agent-callable tools for creating, updating, querying, and deleting calendar, contact, and todo resources on a DAV server.

An MCP server that gives AI agents access to up-to-date documentation from 10,000+ open-source projects. Uses a 'Cabinet' system to lock documentation queries to a specific tech stack (e.g., Next.js 16 + Drizzle ORM + Better Auth), filtering out irrelevant results. Supports both remote HTTP and local stdio transports, with team sharing of Cabinets and API keys. Exposes two MCP tools: query_docs for documentation search and fetch_url for full content retrieval.

Provides a Model Context Protocol (MCP) server exposing tools, prompts, and resources to query Erick Wendel’s public contributions (talks, posts, videos) with filtering and pagination.

memory-lancedb-pro is an OpenClaw plugin that provides long-term “memory” storage and hybrid retrieval on top of LanceDB. It combines vector (ANN) search with BM25 full-text search, fuses results, applies cross-encoder reranking, and runs a multi-stage scoring pipeline including recency/importance/length normalization/time decay plus diversity (MMR). It also supports multi-scope isolation, auto-capture/auto-recall hooks in the OpenClaw lifecycle, optional Markdown mirroring, long-context embedding chunking, and a management CLI for memory CRUD/migration/reindexing.

Open-source LLM observability and evaluation platform for tracing, debugging, monitoring, and optimizing generative AI applications including RAG systems and agentic workflows. Provides comprehensive tracing infrastructure, LLM-as-a-judge evaluation metrics, experiment management, and production dashboards.

MCP server providing programmatic access to Oracle OCI Process Automation for building and managing enterprise business process automation and workflow orchestration.

High-deliverability transactional email API focused on fast inbox delivery for password resets, receipts, and critical notifications.

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.

Arduino's cloud IoT platform API for managing devices, properties, and dashboards, enabling remote monitoring and control of Arduino and compatible IoT devices.

Three-part system (Chrome extension + Node.js server + MCP server) that lets AI coding assistants monitor browser console logs, network traffic, take screenshots, analyze DOM elements, and run Lighthouse-based audits for accessibility, performance, SEO, and best practices directly from MCP-compatible IDEs.

Provides an MCP server that lets an AI agent (e.g., Claude Desktop/Cursor IDE) create, manage, and monitor n8n workflows via natural language, including multi-instance routing across multiple n8n environments.

OpenAI's API providing access to GPT-4, GPT-4o, DALL-E, Whisper, TTS, and embedding models for language, vision, image, audio, and multimodal AI capabilities.