发现优秀的 MCP 服务器

claude-news

Claude Real Time News Popy21/claude-news-mcp https://claudenews.online/api/mcp

image-mcp

MCP server for generating images via text-to-image and image-to-image using lk888 API, returning base64 PNG and metadata.

@avclabs.ai/enhance-mcp

Enables video enhancement through MCP tools for creating tasks, querying status, and synchronous enhancement, supporting URL or local file inputs.

io.github.amanhij/zikkaron

A persistent memory engine for Claude Code that provides MCP tools for storing, retrieving, and reconstructing project context, with features like hippocampal replay and intelligent forgetting.

Author Style "-esque" MCP Server

Provides a catalog of curated author writing styles and tools to blend or analyze them across eight dimensions for text and image prompt generation. It enables users to apply structured literary patterns through deterministic style modeling and coordinate-based interpolation.

mimo-vision-mcp

A lightweight MCP stdio server that enables LLM agents to invoke the MiMo Vision model for local image understanding and OCR via the OpenCode API.

wow-char-export

Analyzes World of Warcraft TBC Classic character gear and talents in real time, enabling natural language queries about hit caps, BiS items, and slot upgrades.

arcade-azure-devops-mcp

An MCP server that enables AI assistants to interact with Azure DevOps projects, work items, repositories, pipelines, wikis, and more via 21 tools.

Markdown to HTML MCP Server

An MCP server that converts Markdown to HTML, supporting both stdio and HTTP interfaces for easy integration with Cursor and other MCP clients.

Webhooks MCP

Enables sending HTTP requests to webhooks with dynamic parameters, supporting all HTTP methods (GET, POST, PUT, PATCH, DELETE), custom headers, and configurable timeouts with detailed error handling and validation.

Cloud Agent MCP Server

Enables AI assistants to create and manage Cursor Cloud Agents that autonomously work on GitHub repositories, including creating tasks, monitoring progress, and automatically generating pull requests.

MNCS Forge MCP

An experimental MCP server for MNCS-native development and evidence control, enabling Codex to manage project authority, candidate lineage, evidence gaps, and evaluator-mode boundaries.

BMAD MCP Server

Provides intelligent agent routing with 5 specialized AI agents (analyst, architect, dev, pm, qa) through OpenRouter integration. Enables unified project structure across all IDEs with global registry management and automated BMAD methodology workflows.

session-clock

A minimal remote MCP server that gives an AI assistant a clock via a single 'now' tool, enabling models to timestamp exchanges and answer "how long ago" questions with best-effort, stateless time capture.

SGU MCP Server

Provides access to geological data from Sveriges Geologiska Undersökning (SGU), including bedrock geology, soil types, and point queries.

UI Reviewer MCP

MCP-first UI/UX review layer for AI-generated frontends. Enables reviewing web pages via URL, capturing screenshots, extracting layout metrics, and generating structured repair plans for agents.

DecisionMatrix MCP

Provides a transparent, deterministic multi-criteria decision analysis engine that ranks options against weighted criteria with exact, explainable results.

obsidian-rag

Provides semantic search over Obsidian markdown notes using BAAI/bge-m3 embeddings and ChromaDB, accessible via the Model Context Protocol.

mcp-rag

Enables per-project, traceable access to a RAG knowledge base, with tools for searching and adding knowledge chunks.

Initial thoughts

Okay, here's the translation of "Convert OpenAPI specifications to MCP server ready tools" into Chinese, along with some considerations for accuracy and context: **Option 1 (Most Direct Translation):** * **将 OpenAPI 规范转换为 MCP 服务器就绪的工具** * (Jiāng OpenAPI guīfàn zhuǎnhuàn wèi MCP fúwùqì jiùxù de gōngjù) This is a fairly literal translation. It's understandable but might sound a bit technical. **Option 2 (More Natural and Common Phrasing):** * **把 OpenAPI 规范转换成可用于 MCP 服务器的工具** * (Bǎ OpenAPI guīfàn zhuǎnhuàn chéng kěyòng yú MCP fúwùqì de gōngjù) This version uses "把...转换成..." which is a common and natural way to express "convert...to..." in Chinese. "可用于" (kěyòng yú) means "can be used for/in". **Option 3 (Emphasizing "Tools Ready for Use"):** * **将 OpenAPI 规范转换为适用于 MCP 服务器的即用工具** * (Jiāng OpenAPI guīfàn zhuǎnhuàn wèi shìyòng yú MCP fúwùqì de jíyòng gōngjù) This option uses "适用于" (shìyòng yú), meaning "suitable for" or "applicable to," and "即用" (jíyòng), meaning "ready to use" or "out-of-the-box." This emphasizes that the tools are immediately usable. **Option 4 (Focusing on Generation):** * **从 OpenAPI 规范生成 MCP 服务器可用的工具** * (Cóng OpenAPI guīfàn shēngchéng MCP fúwùqì kěyòng de gōngjù) This option uses "从...生成..." (cóng...shēngchéng...), meaning "generate from..." This is appropriate if the process involves generating the tools from the OpenAPI specification. **Which option is best depends on the specific context:** * If you want a simple and direct translation, **Option 1** is fine. * If you want a more natural and common phrasing, **Option 2** is a good choice. * If you want to emphasize that the tools are immediately usable, **Option 3** is best. * If the process involves generating the tools from the OpenAPI specification, **Option 4** is the most accurate. **Key Vocabulary:** * **OpenAPI 规范 (OpenAPI guīfàn):** OpenAPI Specification * **转换 (zhuǎnhuàn):** Convert, transform * **MCP 服务器 (MCP fúwùqì):** MCP Server * **就绪 (jiùxù):** Ready * **工具 (gōngjù):** Tools * **可用于 (kěyòng yú):** Can be used for/in * **适用于 (shìyòng yú):** Suitable for, applicable to * **即用 (jíyòng):** Ready to use, out-of-the-box * **生成 (shēngchéng):** Generate * **从...生成... (cóng...shēngchéng...):** Generate from... **Recommendation:** Without more context, I would recommend **Option 2: 把 OpenAPI 规范转换成可用于 MCP 服务器的工具** as it's the most natural and generally applicable. However, consider **Option 4** if the process is about *generating* the tools.

glif-mcp

镜子 (jìng zi)

Adobe Experience League MCP Server

Enables AI assistants to search and fetch documentation content from Adobe Experience League, allowing natural language queries to retrieve Adobe product documentation and articles.

NOVA MCP Security Gateway

A prompt-validation service that checks incoming prompts against security rules, blocking those matching high-severity security or jailbreak patterns while authorizing safe prompts.

selvin-search-mcp

A local web search MCP server supporting parallel, API, and model-based search modes, integrating Zhipu Web Search API and online models for real-time information retrieval.

mcp-toolkit

A general-purpose MCP server providing web search, persistent memory storage, and secure code execution capabilities. It enables AI agents to search the web, store and retrieve data, and run Python/JavaScript code in sandboxed environments.

App Store Connect MCP Server

A server implementing Model Context Protocol for interacting with the App Store Connect API, enabling management of iOS, macOS, and tvOS apps through MCP-compatible clients like Claude Desktop and Cline.

Enterprise SQL & Postgres C# MCP Server

Hardened C# Model Context Protocol (MCP) server for MS SQL Server and PostgreSQL databases featuring read-only transaction safeguards, command security filters, and path traversal protection.

ServiceNow MCP Server

An implementation that enables Claude to connect to ServiceNow instances, allowing it to retrieve data and perform actions through the ServiceNow API.

Banco de Ideas MCP Server

Connects AI agents to a collective creativity platform where they can publish, read, and explore creative connections (bisociations) between concepts from different domains.

mempalace-mcp-http

Enables remote access to the MemPalace MCP server via HTTP, supporting bearer token authentication and concurrent clients while exposing all mempalace tools.