发现优秀的 MCP 服务器

SagaSmith Narrative MCP

Enables long-form tabletop narrative play with durable campaigns, profiles, conflict phases, and branching storylines. Provides session-scoped MCP tools for lobby and play phases, including administrator controls for access, snapshots, and branches.

Brightspace MCP Server

Enables Purdue University students to access their Brightspace academic data including courses, assignments, and grades through web scraping with Duo Mobile 2FA authentication. Provides programmatic access to student academic information when official API access is restricted.

HCM-LLM MCP Server

A FastAPI-based server that enables AI assistants to perform Highway Capacity Manual (HCM) transportation engineering calculations and semantic searches over HCM documentation. It provides specialized tools for complete Chapter 15 two-lane highway analysis following standard engineering methodologies.

jiuyan-mcp

Enables retrieving data from 韭研公社 (jiuyangongshe.com) including timelines, hot rankings, article search, and community feeds, with optional login-protected features like stock movements and follow feeds, all without a browser.

browser-mcp

Agent-native browser control MCP server that enables AI agents to browse and interact with web pages via accessibility tree snapshots and ref ID-based commands.

dwd-mcp

Enables access to German weather data from the Deutscher Wetterdienst, including station observations, forecasts, and warnings, through standardized MCP tools.

Prefeitura MG Juatuba: Certidão Negativa de Débitos

Provides read-only consultation of negative debt certificates (Certidão Negativa de Débitos) from the Juatuba city prefecture in Minas Gerais, Brazil, through a single official tool.

nodriver-mcp-server

An undetected browser automation MCP server powered by nodriver, enabling AI agents to browse, scrape, and automate Chrome while evading anti-bot detection like Cloudflare. It offers 57 tools for navigation, snapshots, screenshots, session management, and more, with one-command setup for major MCP clients.

YouTube MCP Server Enhanced

Enables comprehensive YouTube data extraction and analysis using yt-dlp, including video metadata, channel statistics, playlists, comments, transcripts, search, trending videos, and engagement analytics with intelligent caching and batch processing.

renderping

Enables AI agents to render website screenshots and PDFs, check page changes, and retrieve usage stats via REST calls.

Spring Web to MCP Converter 🚀

Okay, here's a translation of "Convert Spring REST API to MCP Server with OpenRewrite" into Chinese, along with some considerations for different nuances: **Option 1 (More Literal, General):** * **中文:** 使用 OpenRewrite 将 Spring REST API 转换为 MCP 服务器 * **Pinyin:** Shǐyòng OpenRewrite jiāng Spring REST API zhuǎnhuàn wèi MCP fúwùqì * **Explanation:** This is a straightforward translation. It's suitable if you're talking about a general process or concept. **Option 2 (More Technical, Emphasizing the Transformation):** * **中文:** 使用 OpenRewrite 重构 Spring REST API 为 MCP 服务器 * **Pinyin:** Shǐyòng OpenRewrite chónggòu Spring REST API wèi MCP fúwùqì * **Explanation:** "重构 (chónggòu)" means "refactor." This is a better choice if you're emphasizing the code transformation aspect of using OpenRewrite. It implies that you're changing the structure of the code to fit the MCP server architecture. **Option 3 (More Specific, Implying Migration):** * **中文:** 使用 OpenRewrite 将 Spring REST API 迁移到 MCP 服务器 * **Pinyin:** Shǐyòng OpenRewrite jiāng Spring REST API qiānyí dào MCP fúwùqì * **Explanation:** "迁移 (qiānyí)" means "migrate." This is suitable if you're talking about moving the API from one platform (Spring) to another (MCP). **Option 4 (Most Concise, Assumes Context):** * **中文:** OpenRewrite 实现 Spring REST API 到 MCP 服务器的转换 * **Pinyin:** OpenRewrite shíxiàn Spring REST API dào MCP fúwùqì de zhuǎnhuàn * **Explanation:** This is the most concise. It assumes the reader already knows you're using OpenRewrite to *do* the conversion. "实现 (shíxiàn)" means "implement" or "achieve." **Which one to choose depends on the context:** * If you're introducing the idea for the first time, Option 1 or 2 is good. * If you're talking to someone familiar with the process, Option 4 is fine. * If you're specifically talking about moving the API to a new platform, Option 3 is best. **Important Considerations:** * **MCP Server:** Make sure the reader understands what "MCP Server" refers to. If it's a specific product or technology, you might need to provide more context or a brief explanation elsewhere. * **OpenRewrite:** Assuming the audience knows what OpenRewrite is. If not, a brief explanation might be needed. I would probably lean towards **Option 2 (重构)** if I were talking to a technical audience about the code changes involved. If it's a more general audience, **Option 1 (转换)** is safer.

ExternalAttacker MCP Server

一个模块化的外部攻击面测绘工具，集成了自动化侦察和漏洞赏金工作流程的工具。

PromStack MCP Server

Enables Claude Desktop and other MCP-compatible tools to directly access and execute prompts from PromStack, including prompt discovery, selection recommendations, and exporting prompts as Claude Skills.

FlatCash MCP Server

Enables AI agents to buy, hold, and transfer CPI-pegged FLAT stablecoin without wallets or gas. Provides tools for earning through tasks, trading, and managing balances via MCP.

mcp-zettel

An MCP server that provides Claude and other MCP clients with persistent memory through a Zettelkasten knowledge base of interconnected markdown notes. It enables LLMs to create, search, link, and reference atomic notes across sessions without requiring manual copy-pasting.

Indigo MCP Server Plugin

A Model Context Protocol server that enables AI assistants like Claude to interact with Indigo home automation systems through natural language queries for searching and controlling devices, variables, and actions.

Umami MCP Server

MCP server exposing Umami analytics (Cloud + self-hosted)

forecast-mcp

A Model Context Protocol server that provides Monte Carlo forecasting tools for project duration, cost, completion dates, and sensitivity analysis using three-point estimates and historical throughput.

Execution System MCP Server

Enables AI-native task and project management through natural language conversation with Claude, eliminating app-switching by letting you add actions, manage projects across multiple areas of focus, and maintain a GTD-style execution system directly in chat.

Tableau MCP

A suite of developer primitives that enable AI applications to integrate with Tableau, including tools to query data, explore content, and get views.

Unofficial Overleaf MCP Server

Enables AI agents to interact with Overleaf projects directly, including creating projects, managing files, and editing documents in real-time using Overleaf's native Operational Transformation protocol.

OpenSCAD MCP Server

Enables AI assistants to create and manipulate 3D CAD models using OpenSCAD.

CoverageUnlocked MCP Server

Enables AI assistants to analyze insurance denial appeals, providing win probabilities, appeal strategies, payer behavioral intelligence, and regulatory leverage for any CPT code.

Yuque MCP Server

Exposes Yuque knowledge base to AI assistants for searching, creating, and managing documents and books via the Model Context Protocol.

lsfusion-mcp

Enables RAG-powered documentation search using OpenAI embeddings and Pinecone vector database. Provides an extensible framework for adding additional tools with support for both local STDIO and production HTTP transports.

MCP Claude Hacker News

Enables Claude Desktop to interact with Hacker News, fetching articles, searching, and viewing comments.

mcp-sparql

MCP server exposing SPARQL query functionalities for LLMs, enabling query execution, validation, and graph exploration across SPARQL endpoints.

TODO MCP Server

A minimal Model Context Protocol server implementation that provides tools for managing a to-do list, allowing users to create tasks, list them, and mark them as completed via JSON-RPC calls.

q-sys-mcp

Enables AI agents to inspect and control Q-SYS audio/video systems via the QRC protocol over TCP, against a real Core or Q-SYS Designer emulator.

Document Systems

A stateless MCP server for composing, validating, auditing, and rendering consequential documents from a small semantic model.