Latest MCP Servers

Builds a semantic graph of TypeScript codebases, enabling AI assistants to perform deep, cross‑file reasoning, impact analysis, and natural‑language queries.

Self‑hosted Claude Code workspace with multi‑provider routing, sandboxed execution, and a full in‑browser IDE.

Provides a self‑hosted Claude Code workspace that integrates multi‑provider routing, sandboxed code execution, and a full web‑based IDE.

Generate FastMCP 3.x servers directly from OpenAPI 3.0.x/3.1.x (or Swagger 2.0) specifications, delivering production‑ready code with built‑in JWT/OAuth2 authentication, modular sub‑servers, middleware stack, Pydantic validation, auto‑generated tests and optional event store.

Command‑line utilities for creating and managing TanStack Start full‑stack SSR apps, TanStack Router SPAs, and installing ecosystem add‑ons and libraries.

Provides a Model Context Protocol server that lets AI assistants query CKAN open data portals for datasets, organizations, groups, tags, and DataStore tables using natural language, without requiring direct knowledge of CKAN APIs.

A powerful, extensible multi‑agent workflow engine built with Python and FastAPI, enabling dynamic tool invocation, visual workflow orchestration, real‑time monitoring, sandboxed code execution, and MCP integration.

Enables AI agents to control the Tabby terminal through an MCP server, providing full command execution, tab and profile management, and SFTP file operations from AI assistants.

Provides a Home Assistant add‑on that exposes a safe REST API, allowing AI‑enabled IDEs such as Cursor, VS Code, Claude, and any MCP‑compatible editor to analyze, create, and deploy automations, Lovelace dashboards, themes, HACS integrations and more using natural‑language commands.

Provides a local‑first bridge that enables Claude to read, search, and send messages using an existing Slack user session, supporting both stdio/web workflows and a secure hosted HTTP endpoint.

Provides semantic code search, AI‑powered prompt enhancement, planning, execution tracking, persistent memories, and advanced code review through a local‑first MCP server built on the Auggie SDK.

Provides a markdown‑first Model Context Protocol server for Notion, consolidating dozens of REST endpoints into composite actions that are token‑efficient and ready for AI agents.

Provides browser automation via a Model Context Protocol server that controls a real Chrome instance, enabling fast, parallel, authenticated interactions for AI agents.

Provides a free, no‑auth REST endpoint that aggregates real‑time cryptocurrency news from 200+ sources, supports historical archive queries, multi‑language translation, AI‑powered analysis, and embeddable widgets.

Enables AI assistants to search, retrieve, analyze, and summarize arXiv papers, offering author/category browsing, trend tracking, citation insights, and multi‑format exports.

Search and read over 100 million offline articles from ZIM archives via a fast, API‑first knowledge server.

Retrieve token‑optimized, structured YouTube data—including video details, transcripts, channel statistics, trending lists, and comments—for direct consumption by large language models.

Provides an open‑source platform to build, evaluate, and ship production‑ready retrieval‑augmented generation (RAG) and agentic applications, offering end‑to‑end tooling from ingestion to hosting.

Provides AI‑driven conversational access to Wazuh SIEM data, allowing natural‑language queries, threat analysis, incident triage, and compliance checks through a Model Context Protocol‑compliant remote server.

Manages AFFiNE workspaces, documents, comments, version history, users, tokens, notifications, and blob storage via a Model Context Protocol server that communicates over stdio.

Provides token‑efficient, structured MCP servers that wrap popular developer tools and return typed JSON for AI coding agents, dramatically reducing token usage while preserving full machine‑readable data.

Manage Spaceship domains, DNS records, contacts, and marketplace listings via natural language through an MCP server.

Provides AI‑powered analysis of images and videos using Google Gemini or Vertex AI, supporting URLs, local files, and base64 inputs, and returning detailed descriptions, comparisons, object detection with annotated output, and video summarization.

Provides a lightweight, embedded graph‑based memory system that stores and recalls contextual information for AI applications without requiring external LLM calls.

Provides Bitcoin and Lightning knowledge tools for AI agents, accessible via pay‑per‑use Lightning (L402) invoicing and a Web of Trust scoring API.

Provides Claude access to Google Drive, Docs, Sheets, Slides, Calendar, Gmail, and Contacts via an MCP server.

Provides an MCP server that keeps .faf project DNA in perpetual sync with CLAUDE.md, delivering zero‑drift AI context for any LLM.

Provides a catalog of reusable agent skills, custom agent templates, and MCP server configurations to extend AI coding agents with Azure SDKs and Microsoft AI Foundry capabilities.

Provides a remote Model Context Protocol service that proxies Sentry's API, enabling AI‑powered development tools to query, search, and act on Sentry data directly from code editors.

Provides interaction with EMQX MQTT brokers, allowing Model Context Protocol clients to list, inspect, disconnect MQTT clients and publish messages to topics with configurable QoS and retention.

Provides instant, AI‑native access to the full text of 47 EU regulations, enabling developers and compliance professionals to query articles, recitals, and definitions directly from Claude, Cursor, or any MCP‑compatible client.

Enables a one‑command setup that configures Claude Code environments, auto‑generates stack‑aware agents, slash commands, enforcement hooks, and integrates MCP servers for any tech stack.