Browse MCP servers — page 9
Explore the next set of open-source servers for connecting AI tools to data and workflows.
executor
rhyssullivan
Local AI executor with a CLI, local API server, and web UI. Starts a local runtime with a web UI at http://127.0.0.1:4788. Supports MCP-compatible agents for tool catalog sharing.
Lanhu MCP Server
dsphper
A powerful MCP server for automatically extracting and analyzing Lanhu design documents. Requires setting environment variables for Lanhu Cookie and optionally Feishu webhook URL for team collaboration features.
Lightswind UI
codewithMUHILAN
The world's first AI-native, CLI-first component library for React with an integrated MCP server allowing AI coding assistants to browse, fetch, and install components autonomously inside your codebase.
arcticdb-mcp
YMuskrat
MCP server that gives AI assistants full read/write access to ArcticDB. Requires setting ARCTICDB_URI environment variable or MCP client config to specify the path or connection string to the ArcticDB database.
Vibetest Use
browser-use
Automated QA testing using Browser-Use agents to test websites for UI bugs, broken links, accessibility issues, and other technical problems. Requires a Google API key configured via environment variable GOOGLE_API_KEY.
Telegram MCP Server
chigwell
Integration with Telegram implemented via the Model Context Protocol (MCP). Requires external configuration through a .env file, including settings such as TELEGRAM_API_ID, TELEGRAM_API_HASH, TELEGRAM_SESSION_STRING, or TELEGRAM_SESSION_NAME for session management.
Context Portal MCP (ConPort)
GreatScottyMac
用于管理结构化项目上下文的模型上下文协议(MCP)服务器。需要 Python 3.8 及以上版本,可选使用 'uv' Python 环境管理器。自动为每个工作区创建 SQLite 数据库。支持向量嵌入以实现语义搜索和增强检索生成(RAG)。
论文搜索 MCP
openags
用于搜索和下载来自多个来源(包括 arXiv、PubMed、bioRxiv、medRxiv、Google Scholar 以及 IACR ePrint Archive)的学术论文的 MCP 服务器。支持与大型语言模型(如 Claude Desktop)集成。
Hippo
kitfunso
Biologically-inspired memory system for AI agents. Decay by default, strength through use. Uses SQLite under the hood with zero runtime dependencies. Optional embeddings require local Transformers.js or API keys configured via environment variables.
Fetcher MCP
jae-jae
MCP server for fetching web content using Playwright headless browser. Supports intelligent content extraction and flexible output formats. Requires Playwright browser installation via 'npx playwright install chromium'.