Top MCP Servers

Provides a way to navigate complex OpenAPI specifications using simple language, enabling AI models to understand and explore APIs without writing code.

Provides a Model Context Protocol server that enables AI assistants to send, read, search, and organize Gmail messages, supporting attachments, label and filter management, and automatic OAuth2 authentication.

Provides a server that interfaces with the Notion API, enabling LLMs to retrieve, modify, and query Notion workspace data, with optional Markdown conversion to reduce token usage.

Provides a native Go‑based implementation that exposes Kubernetes and OpenShift resources via the Model Context Protocol, enabling AI agents and other clients to perform CRUD operations, pod management, Helm actions, and more without external CLI tools.

Open-source antivirus for AI agents that blocks risky tools, secret exposure, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Provides real‑time web search, intelligent data extraction, structured website mapping, and systematic crawling through an MCP server, ready to be integrated with AI coding assistants and other tools.

Provides enterprise‑grade open source software supply chain security by scanning source code, dependencies, containers and SBOMs, detecting vulnerabilities and malicious packages, and enforcing policy as code.

Provides Google Calendar integration for AI assistants, enabling event listing, creation, updating, deletion, free/busy queries, recurring event handling, and smart scheduling via natural language.

Enables AI agents to control web browsers via the browser-use protocol, supporting both SSE and stdio transports, with VNC streaming and asynchronous task execution.

Enables bidirectional integration of large language models with ROS‑enabled robots, allowing natural language commands and real‑time access to robot state, topics, services and parameters.

Enables persistent, cross‑session context for AI coding assistants by storing tickets, issues, roadmaps, handovers, and other project artifacts in a standardized `.story/` directory, accessible via CLI, MCP server, and Claude Code/Codex skills.

Enables Claude AI to control QGIS through a socket‑based server, allowing direct project creation, layer manipulation, processing execution, and arbitrary Python code execution within the desktop GIS environment.

Enables real-time interaction with Jupyter notebooks, allowing AI to edit, document, and execute code for data analysis, visualization, and multimodal output.

Provides a project‑specific memory bank that stores decisions, progress, architecture, and custom data, exposing a structured knowledge graph via MCP for AI assistants and IDE tools.

Enables natural‑language interaction with Neo4j databases, allowing large language models to query, modify, and manage graph data through multiple transport modes.

Manage Docker containers, images, networks, and volumes using natural language commands via an MCP server.

Provides controlled SSH access for LLM agents with command classification, policy‑based authorization, human‑in‑the‑loop approval, and immutable audit logging.

Fetches web content and returns it in HTML, JSON, plain‑text, or Markdown formats, optionally applying custom request headers.

Provides a Model Context Protocol server that enables interaction with MongoDB databases and MongoDB Atlas clusters through a unified API.

Enables AI assistants to perform deep, semantic code search, repository analysis, and package discovery across public and private GitHub repositories, delivering structured, AI‑optimized context for development workflows.

Enables AI assistants to run read‑only ClickHouse queries, list databases and tables, and execute embedded chDB queries through an MCP interface.

Provides tools to scrape, extract structured data, crawl webpages, and access general‑purpose browser agents such as OpenAI CUA, Anthropic Claude Computer Use, and lightweight Browser Use via a Model Context Protocol server.

Enables AI assistants to invoke any Apify Actor as a tool, providing real‑time web scraping, data extraction, and automation via the Model Context Protocol.

Aggregates multiple MCP resource servers and serves them via a single HTTP endpoint, supporting SSE and HTTP streaming transports.

Provides a Model Context Protocol server that exposes a rich set of dbt‑related tools—SQL execution, semantic‑layer queries, discovery APIs, dbt CLI commands, admin operations, code generation, lineage analysis, and product documentation retrieval—so AI agents can safely interact with dbt projects and platforms.

Enables AI assistants to read, create, edit, and manage notes and tags within an Obsidian vault, providing searchable, writable access to vault contents.

Offers an MCP server that lets LLMs, agents, and IDEs run Semgrep scans to detect security vulnerabilities in source code.

Provides an all-in-one sandbox environment that combines Browser, Shell, File operations, MCP services, and VSCode Server inside a single Docker container, enabling unified, secure execution for AI agents and developers.

Enables adversary emulation for AI agents, LLM applications, and MCP servers, letting teams test their AI systems against realistic attack scenarios.

Provides a client SDK for building AI‑native applications on Baidu Cloud, enabling model calls, component orchestration, knowledge‑base management, workflow composition, monitoring, and flexible deployment options.

Provides secure, programmatic access to the local filesystem via the Model Context Protocol, enabling read, write, copy, move, delete, and search operations with built‑in path validation and MIME type detection.

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.