Browse MCP servers — page 11
Explore the next set of open-source servers for connecting AI tools to data and workflows.
Apple Doc MCP
MightyDillah
MCP 服务器,提供无缝访问 Apple 开发者文档,支持智能搜索和通配符。需要 Node.js 18.0.0 或更高版本,以及连接到 Apple 文档 API 的互联网连接。
Haiku RAG
ggozad
Opinionated agentic RAG powered by LanceDB, Pydantic AI, and Docling. Requires Python 3.12 or newer. Supports document management, search, QA, and analysis with multimodal and vision-capable features. External embedding providers (Ollama, OpenAI, etc.) are required and configured separately.
Meta Ads MCP
nictuku
Model Context Protocol (MCP) server for interacting with Meta Ads API. Enables AI models to access, analyze, and manage Meta advertising campaigns through a standardized interface. Requires PIPEBOARD_API_TOKEN environment variable for authentication with Pipeboard service.
managed-agents
sandbaseai
Local-first, self-hosted AI agent runtime with Claude Managed Agents-style APIs, sandboxed sessions, memory, tools, audit, replay, and a local Console. Requires a model provider API key (OpenAI, Anthropic, or compatible) configured via environment variables.
ClickHouse MCP Server
ClickHouse
An MCP server for ClickHouse. Requires external configuration of ClickHouse connection parameters via environment variables such as CLICKHOUSE_HOST, CLICKHOUSE_USER, CLICKHOUSE_PASSWORD, and optionally CLICKHOUSE_DATABASE.
FreeCAD MCP
neka-nat
用于控制 FreeCAD 的 MCP 服务器,配合 Claude Desktop 使用。需要将 addon/FreeCADMCP 目录放入 FreeCAD 的插件目录(路径因操作系统而异)。运行服务器通过 Claude Desktop 需要预先安装 uvx 工具。
Apple Docs MCP
kimsungwhee
A powerful MCP server providing seamless access to Apple Developer Documentation through natural language queries. Supports searching Apple frameworks, APIs, sample code, and tutorials. No external data files required.
Manim MCP 服务器
abhiemj
一个 MCP 服务器,能够执行 Manim Python 脚本以生成动画并返回渲染后的视频。通过环境变量(如 MANIM_EXECUTABLE)进行配置,以指定 Manim 可执行文件的路径。
Apple Health MCP
Neil Pullman
Query and analyze Apple Health CSV exports with SQL through an in-memory DuckDB database
MCP 客户端 for Ollama
jonigl
A Python 客户端,用于连接 Model Context Protocol 服务器(MCP Server)通过 Ollama,实现本地大模型(LLMs)调用工具。需要在本地运行 Ollama 并使用 Python 3.10+。支持通过 JSON 文件和命令行参数进行配置。