发现优秀的 MCP 服务器

通过 MCP 服务器扩展您的代理能力,拥有 86,267 个能力。

全部86,267
agent-tasks

agent-tasks

Enables pipeline-driven task management for AI coding agents, with stage-gated workflows, dependency tracking, artifact versioning, and multi-agent collaboration.

mcp-google_calendar

mcp-google_calendar

Enables AI agents to interact with Google Calendar through natural language, supporting listing, creating, and searching events across accessible calendars.

mcp-sarb-za

mcp-sarb-za

Enables access to South African Reserve Bank data via natural language queries, part of the Pipeworx MCP gateway.

mcp-jp

mcp-jp

Japanese SMB SaaS connectors for MCP. Includes an L-Step (LINE marketing automation) server exposing 19 tools for friends, tags, and messaging.

shiryan-mcp-server

shiryan-mcp-server

Enables AI agents to access SHIRYAN's change detection, geofencing, and alert synthesis for monitoring pipeline and critical infrastructure corridors in Saudi Arabia via MCP stdio tools.

Ember MCP Server

Ember MCP Server

A Model Context Protocol server that provides tooling support for Ember.js development, allowing developers to execute CLI commands, run codemods, access documentation, and discover community resources.

openai-agents-chat-demo

openai-agents-chat-demo

OpenAI 代理聊天演示。集成自定义 LLM 和 MCP 服务器以及函数工具。 (Or, more literally: OpenAI 代理聊天演示。整合自定义 LLM 和 MCP 服务器以及函数工具。)

mcp

mcp

Okay, here's a translation of "Python implementation of an Elasticsearch MCP server" into Chinese, along with some considerations for different nuances: **Option 1 (Most Literal and Common):** * **Python 实现的 Elasticsearch MCP 服务器** * (Pinyin: Python shíxiàn de Elasticsearch MCP fúwùqì) This is the most direct and common translation. It's easily understood. **Option 2 (More Emphasis on "Implementation"):** * **用 Python 实现的 Elasticsearch MCP 服务器** * (Pinyin: Yòng Python shíxiàn de Elasticsearch MCP fúwùqì) This adds "用" (yòng), meaning "using" or "with." It emphasizes that Python is the *tool* used for the implementation. It's slightly more descriptive. **Option 3 (Slightly More Formal):** * **基于 Python 的 Elasticsearch MCP 服务器实现** * (Pinyin: Jīyú Python de Elasticsearch MCP fúwùqì shíxiàn) This translates to "Elasticsearch MCP server implementation based on Python." It's a bit more formal and might be used in technical documentation. **Option 4 (Focus on Building/Developing):** * **使用 Python 构建的 Elasticsearch MCP 服务器** * (Pinyin: Shǐyòng Python gòujiàn de Elasticsearch MCP fúwùqì) This translates to "Elasticsearch MCP server built using Python." It emphasizes the act of building or developing the server. **Which one to choose?** * For general communication and clarity, **Option 1 (Python 实现的 Elasticsearch MCP 服务器)** is usually the best choice. * If you want to emphasize that Python is the *tool* used, choose **Option 2 (用 Python 实现的 Elasticsearch MCP 服务器)**. * For more formal documentation, **Option 3 (基于 Python 的 Elasticsearch MCP 服务器实现)** might be appropriate. * If you want to emphasize the act of building the server, choose **Option 4 (使用 Python 构建的 Elasticsearch MCP 服务器)**. **Important Notes:** * **Elasticsearch:** This is a proper noun and is generally kept as "Elasticsearch" in Chinese technical contexts. While there are Chinese transliterations, they are not commonly used. * **MCP:** If "MCP" is a well-known acronym within the specific Chinese-speaking community you're targeting, you can leave it as is. If not, you might consider providing a brief explanation of what it stands for in parentheses after the first mention. However, without knowing what MCP stands for in this context, I can't provide a suitable translation. * **服务器 (fúwùqì):** This is the standard Chinese word for "server." Therefore, my recommendation is **Python 实现的 Elasticsearch MCP 服务器** unless you have a specific reason to choose one of the other options. If you can tell me what "MCP" stands for, I can refine the translation further.

Google Search MCP Server

Google Search MCP Server

专为 VS Code / Cline / Anthropic 构建的 MCP 服务器 - 启用 Google 搜索并具备跟踪链接和研究网站的能力

Hanzo MCP

Hanzo MCP

Enables access to Hanzo APIs and Platform capabilities via MCP, along with development tools for managing and improving projects.

yt-analytics-mcp

yt-analytics-mcp

Owner-side YouTube analytics for AI agents: watch time, traffic sources, audience retention, playlist and podcast-series metrics, and episode-over-episode comparison. Read-only, all of it.

youtube-playlists-mcp

youtube-playlists-mcp

A simple MCP server to manage YouTube playlists built in TypeScript.

dad-jokes-mcp

dad-jokes-mcp

Enables fetching and managing dad jokes with tools for random jokes, multiple jokes, categories, and persistent storage.

betbetter-mcp

betbetter-mcp

Provides AI assistants with sports model win probabilities and fair odds across nine sports without requiring an API key.

EVE-NG MCP Server

EVE-NG MCP Server

An MCP server that gives Claude and other LLM agents programmatic access to EVE-NG network labs, enabling creation, configuration, and management of virtual network topologies through natural language.

GitHub PR MCP Server

GitHub PR MCP Server

用于 Github 的 Claude MCP 服务器,集成 Linear

GroupDocs.Metadata MCP Server

GroupDocs.Metadata MCP Server

Exposes GroupDocs.Metadata as AI-callable tools for reading, searching, writing, and removing metadata in documents.

VisualAI MCP Server

VisualAI MCP Server

Enables local AI image generation on Apple Silicon Macs using MLX and Stable Diffusion. Supports conversational design iteration, asset generation, and wireframe creation with zero API costs through the Model Context Protocol.

Godot MCP

Godot MCP

A security-first MCP server and Godot editor addon enabling AI agents to observe and control Godot games through bounded, permission-gated tools for debugging, input automation, and project editing.

SkySQL MCP Server

SkySQL MCP Server

SkySQL MCP 服务器和客户端代码仓库。

Surfmeter MCP Server

Surfmeter MCP Server

A Model Context Protocol server for the AVEQ Surfmeter management API. It exposes typed tools for clients, measurements, anomalies, groups, ISPs, users, keys, capabilities, settings, license usage, and the built-in AI assistant.

Study Database MCP

Study Database MCP

An MCP server that provides deterministic math computation (numeric, symbolic, unit, matrix) and hybrid retrieval over study notes/textbooks with citations, helping Claude become a reliable study partner.

ClickUp MCP Server

ClickUp MCP Server

Securely connect AI assistants to ClickUp workspaces through OAuth 2.0, providing 72 tools across 12 categories for comprehensive task management, time tracking, project planning, and workspace operations without managing API keys.

OmniKit

OmniKit

Free, fully-offline MCP utility tools for agents: base64, UUID, JSON validation, SHA hashing, timestamps, URL codec, case conversion, and secure passwords. No API keys, no tracking, works offline - stdlib-only Python stdio server.

seedbase-mcp

seedbase-mcp

Enables AI assistants to generate realistic, relationship-preserving test data from Seedbase projects into databases.

GitLab MCP Server

GitLab MCP Server

Enables AI agents to interact with GitLab via a restricted set of 9 tools using OAuth 2.0 authentication, supporting merge requests, comments, pipelines, and labels.

RecruiterCheck MCP

RecruiterCheck MCP

MCP server for scam-risk checks on job postings, recruiter emails, and company domains.

CorelDRAW Live MCP

CorelDRAW Live MCP

Enables control of an already open CorelDRAW document via MCP, with live editing, atomic undo, and safe coordinate-based operations. Supports Windows-only COM automation and integrates with desktop AI clients like Claude Desktop.

icon-search-mcp

icon-search-mcp

A Model Context Protocol server that enables unified fuzzy searching across multiple icon libraries (Bootstrap, Feather, Octicons, Tabler) with intelligent caching and comprehensive filtering options.

Notion Schedule Agent

Notion Schedule Agent

An MCP server that turns your Notion task list into an AI-optimized daily schedule, reading tasks with page content and priorities from an Eisenhower matrix, and writing a clean schedule back to Notion.