Latest MCP Servers

Enables AI assistants to control Home Assistant devices, query states, execute services, and manage automations using natural language.

Render and preview Mermaid diagrams with live‑reload, multiple export formats, theme support, and an integrated Claude skill for expert diagram guidance.

Run controlled experiments that compare an MCP server‑enabled LLM against a baseline LLM on real software‑engineering tasks such as bug‑fixing, exploit generation, and tool‑selection, producing quantitative performance metrics.

Search and retrieve over 200,000 icons from more than 150 collections, usable via a command‑line interface or as an MCP server for AI coding assistants.

Provides real-time and historical stock market data through MCP endpoints for LLMs and agentic workflows, enabling seamless access to comprehensive financial information.

A CLI‑first knowledge layer that gives AI persistent memory of project context, enabling tasks, linked documentation, and built‑in time tracking while keeping everything version‑controlled in a local .knowns folder.

Provides hot‑reloadable prompt templates with chainable steps, quality gates, and structured reasoning frameworks for Claude and compatible MCP clients.

Enables generation of PlantUML diagrams through a Model Context Protocol (MCP) server, returning embeddable SVG/PNG URLs and optional local file saving.

Automatically format Markdown articles and publish them to WeChat public accounts, supporting theme selection, image upload, and AI integration.

Generate images from text prompts using the Z‑Image‑Turbo model via a command‑line interface, a modern web UI, or an MCP server, with automatic GPU acceleration for NVIDIA CUDA, Apple Silicon MPS, and AMD ROCm.

Command-line interface that enables querying, creating, synchronizing, and managing Tana workspaces, supporting full‑text and semantic search, batch operations, and an MCP server for AI tool integration.

Enables AI assistants to work with documents that exceed their context window by storing content externally, providing search, code execution, evidence tracking, and recursive sub‑agents via an MCP server.

Provides a knowledge‑graph memory server backed by DuckDB, enabling fast, scalable storage, fuzzy search, and relational queries over entities, observations, and relations.

Provides a secure, unified endpoint for routing all MCP traffic, enforcing RBAC, policies, and full observability while supporting deployment on Docker, Kubernetes, Bun, or Node.

Provides persistent memory, semantic code search, and graph‑based analysis for AI tools through an MCP server.

Provides intelligent semantic code search for AI assistants by indexing codebases with local AI model embeddings and exposing searchable context through the Model Context Protocol.

Automates X/Twitter tasks such as profile scraping, follower management, tweet searching, liking, retweeting, posting, and multi‑account actions through a CLI, browser console scripts, Node.js API, and an MCP server for AI agents, all without requiring Twitter API keys or fees.

Provides fast, local‑first code indexing and search across dozens of programming languages, enabling LLMs and developers to retrieve symbols, definitions, and code snippets with sub‑100 ms latency.

Enables AI assistants to query PortOne's developer and help center documentation, retrieve channel lists, add test channels, view sub‑store information, and obtain payment histories through the Model Context Protocol.

Provides an extensible platform for AI‑augmented document ingestion, hybrid (vector + full‑text + graph) retrieval, automatic knowledge‑graph construction, and conversational query answering, with front‑ends in React, Angular, and Vue and a FastAPI‑based backend.

Provides AI‑enhanced analysis of NPM packages, delivering version history, dependency mapping, security vulnerability scanning, size metrics, and quality scores through the Model Context Protocol.

Unifies ACK cluster management, native Kubernetes operations, observability, security audit and diagnostic capabilities into a single AI‑native toolset, allowing natural‑language interaction with AI assistants to perform complex container‑oriented AIOps tasks.

Provides comprehensive web performance, accessibility, SEO, and security audits using Google Lighthouse, enabling AI agents to evaluate and improve websites.

Provides a set of AI‑friendly tools for creating, reading, updating and deleting Backlog resources such as projects, issues, wiki pages, Git repositories and notifications, with optional response optimization and token limiting.

Orchestrates a network of asynchronous agents and streaming swarms to conduct ensemble‑consensus research, automatically creating indexed PGlite databases in WebAssembly and providing semantic, hybrid, and SQL search capabilities.

Provides real-time access to shadcn-svelte component documentation and developer utilities via web scraping, exposed through an MCP server with HTTP and SSE transports.

Provides AI agents instant access to Apple developer documentation through semantic, keyword, and hybrid retrieval‑augmented generation (RAG) techniques.

A unified AI development platform that provides a TypeScript SDK and professional CLI to build, test, and deploy applications across multiple AI providers, with built‑in tools, MCP integration, and enterprise‑grade features such as Redis conversation memory, cost optimization, and multi‑provider failover.

Provides a unified enterprise gateway and registry for discovering, securing, and executing Model Context Protocol (MCP) tools via a standardized HTTP API with sandboxing and OAuth 2.1 support.

Enables AI assistants such as Claude to retrieve, create, review, and upload content in microCMS via a Model Context Protocol server.

Provides programmatic access for AI assistants to query and manage Prometheus Alertmanager resources, supporting authentication, multi‑tenant handling, and pagination to fit LLM context limits.

Provides a production‑ready foundation for building custom Model Context Protocol servers in TypeScript, featuring IP geolocation tools, a full CLI, dual STDIO/HTTP transports, TOON output format, JMESPath filtering, and an extensible 5‑layer architecture.