Packages

SPARQL LLM MCP server enabling AI agents to query and reason over RDF knowledge graphs using SPARQL — generating SPARQL queries from natural language, querying SPARQL endpoints (Wikidata, DBpedia, custom endpoints), and integrating semantic web knowledge graphs into agent-driven research and knowledge retrieval workflows.

Durable workflow engine that executes long-running, fault-tolerant processes with automatic state persistence, retry logic, and exactly-once execution guarantees across distributed systems.

YNAB (You Need A Budget) MCP server enabling AI agents to interact with the YNAB personal budgeting app — querying budget categories and balances, reviewing transactions, tracking spending patterns, and integrating YNAB's envelope budgeting system into agent-driven personal finance analysis and planning workflows.

Official Hugging Face MCP server connecting LLMs to the HF Hub and thousands of Gradio AI applications. Supports STDIO, StreamableHTTP, and stateless JSON-RPC transports with dynamic tool management, proxy tool loading from external MCP endpoints, and OAuth authentication.

Fast, secure MCP server runtime that loads tools as WebAssembly plugins. Plugins can be written in any WASM-compatible language, distributed via OCI registries (Docker Hub, GHCR), and run sandboxed with configurable memory/network/filesystem constraints. Includes 19+ built-in plugins.

A fullstack MCP framework (TypeScript and Python SDKs) for building MCP servers, interactive React-based MCP app widgets, and MCP agents/clients, with built-in inspector tooling and optional cloud deployment via Manufact.

An MCP server that gives AI assistants access to shadcn/ui v4 component source code, demos, usage patterns, and block implementations across React, Svelte, Vue, and React Native frameworks.

Official Airbyte MCP server enabling AI agents to interact with Airbyte's data integration platform — managing connections, triggering syncs, querying connector status, and monitoring data pipeline health.

Graph-based RAG system that parses multi-language codebases using Tree-sitter, builds knowledge graphs in Memgraph, and enables natural language queries about code structure and relationships. Supports parsing 11+ languages, AI-powered Cypher query generation, surgical code editing with AST targeting, shell command execution, and real-time graph updates via file watching. Includes an MCP server for Claude Code integration.

Open-source platform for creating and managing standardized cloud development environments (workspaces) programmatically via REST API, designed for both developer use and agent-driven code execution.

Documentation MCP server enabling AI agents to search and retrieve documentation from local or remote documentation sources — indexing documentation files, performing semantic search over docs, retrieving relevant documentation sections, and integrating documentation retrieval into agent-driven coding and research workflows.

Hono MCP server template enabling developers to build MCP servers using the Hono web framework — providing a TypeScript template for creating remote MCP servers deployable to Cloudflare Workers, Deno Deploy, or other edge runtimes, with built-in routing, middleware, and MCP protocol handling.

MCP server providing knowledge base capabilities with document ingestion, vector embedding, and semantic retrieval. Enables AI agents to build and query local knowledge bases from documents, notes, and structured content — supporting RAG (Retrieval Augmented Generation) patterns for grounding agent responses in domain-specific knowledge.

LLMs.txt Explorer MCP server enabling AI agents to discover and read llms.txt and llms-full.txt files from websites — fetching the standardized machine-readable documentation format that websites publish for LLM consumption, aggregating documentation context from multiple services, and providing agents with structured, LLM-optimized documentation without scraping raw HTML.

MCP Gearbox from GPTScript-AI — a tool aggregation and routing layer for MCP that combines multiple MCP servers into a unified interface, manages MCP tool lifecycles, and provides a single connection point for AI agents to access tools from multiple underlying MCP servers. Simplifies multi-MCP deployments by acting as a composable middleware layer.

MCP server providing formal logic and reasoning capabilities to AI agents. Enables agents to execute Prolog-style logical inference, validate logical constraints, perform knowledge base queries, and use formal logic for verification and reasoning tasks — extending LLM capabilities with symbolic reasoning.

MCP server enabling AI agents to send Apple Events — the macOS inter-application communication protocol used by AppleScript. Allows agents to automate macOS applications (Finder, Mail, Calendar, Safari, etc.) by sending Apple Events programmatically, enabling system-level macOS automation from AI agents.

Node.js Debugger MCP server enabling AI agents to debug Node.js applications — connecting to Node.js debug protocol, setting breakpoints, stepping through execution, inspecting variables and call stacks, and integrating Node.js debugging into agent-driven JavaScript/TypeScript development and troubleshooting workflows.

Official Redis Cloud MCP server enabling AI agents to manage Redis Cloud subscriptions and databases — creating databases, monitoring usage, managing access, and configuring Redis Cloud infrastructure.

Official ScrapeGraph MCP server providing AI-powered web scraping and structured data extraction — using LLMs to extract structured information from web pages without brittle CSS selectors.