Browse MCP servers — page 74
Explore the next set of open-source servers for connecting AI tools to data and workflows.
KiCad MCP Server
Seeed-Studio
Model Context Protocol (MCP) server for KiCad 9.0+ that lets AI assistants analyze schematics, inspect PCBs, trace connections, validate designs, and generate embedded code. Requires external KiCad installation (8.0+, recommended 9.0 or 10.0) and kicad-cli available in PATH.
LocaLLama MCP 服务器(测试分支)
heratiki
用于智能路由编码任务的 MCP 服务器,连接本地 LLM 和免费或付费的 API。需要通过环境变量配置本地 LLM 端点和 OpenRouter API 密钥。支持可选的基于 Python 的 Retriv 模块进行代码搜索,需安装 retriv 及相关依赖。
MCP Ripgrep Server
mcollina
An MCP server that provides ripgrep (rg) search capabilities to any MCP client such as Claude. Requires ripgrep (rg) command installed and available in your PATH.
MobAI MCP Server
MobAI-App
MCP server for MobAI - AI-powered mobile device automation. Requires MobAI desktop app running locally (provides HTTP API on port 8686). Screenshots saved to /tmp/mobai/screenshots/.
Nocturne: The Soul Anchor Protocol
StartTheEvolution
Nocturne Memory is an MCP Server providing long-term persistent memory for AI agents using SQLite. It requires an external SQLite database file configured via the DATABASE_URL environment variable in the .env file, which must be an absolute path on the host system.
Obsidian MCP Server (TypeScript + Bun)
fazer-ai
一个支持模型上下文协议(MCP)的服务器,允许Claude(或任何支持MCP的大型语言模型)通过本地REST API社区插件与您的Obsidian知识库进行交互。需要通过环境变量OBSIDIAN_API_KEY或.env文件传递Obsidian API密钥。
Official MCP Server for Debugg AI
debugg-ai
AI-driven browser automation and E2E test server implementing the Model Context Protocol (MCP), designed to help AI agents test UI changes, simulate user behavior, and analyze visual outputs of running web applications via natural language and CLI tools. Requires an API key configured via the DEBUGGAI_API_KEY environment variable.
OpenRPC MCP Server
user-attachments
OpenRPC MCP server providing JSON-RPC functionality through OpenRPC. No external data files required.
Pinecone Developer MCP Server
pinecone-io
The Pinecone Developer MCP Server allows AI tools to connect with Pinecone projects and documentation, enabling search, index configuration, code generation, and data upsert/search. Requires Node.js runtime. API key configuration is done via environment variable PINECONE_API_KEY.
Powertools for AWS MCP
Amazon Web Services
用于 AWS Lambda MCP 服务器的 Powertools,提供跨多种运行时的 Powertools for AWS Lambda 文档搜索功能。它允许大型语言模型(LLM)代理搜索与工具包相关的文档和示例。