发现优秀的 MCP 服务器

purplemux-mcp

Controls local purplemux (tmux + LLM workspace manager) from Claude Code/Codex, enabling cross-LLM orchestration by managing workspaces, tabs, terminals, and Electron browser via 16 tools.

weather-mcp

Provides real-time weather data and alerts from the National Weather Service API, including forecasts for US locations and active alerts for US states.

Emergency Medicare Planner MCP Server

与谷歌地图集成，可在紧急情况下定位和评估医疗机构，根据用户的医疗需求、紧急程度和机构能力，帮助用户找到合适的医院和诊所。

honcho-mcp-web

Remote MCP server (HTTP/OAuth) exposing a self-hosted Honcho instance to claude.ai custom connectors and other MCP clients.

claw-mcp-toolkit

All-in-one MCP toolkit with 29 tools across 5 modules: crypto prices, web utilities, social media, finance tracking, and productivity. MIT licensed.

Specky

An MCP server for Spec-Driven Development that transforms natural language ideas and meeting transcripts into structured, production-grade specifications using EARS notation. It automates a 7-phase pipeline to generate project artifacts like requirements, architecture designs, and task lists directly to disk.

Dataverse MCP Server

Enables AI agents to query, inspect, and manage Microsoft Dataverse records, metadata, schema, forms, views, and Power Platform environments via the Dataverse OData Web API.

TaskDoc MCP

Enables management of Kanban-backed task checkpoint documents in Obsidian, supporting task creation, querying, checkpoint commits, and rich block storage via MCP tools.

Google Calendar MCP Server

Google 日历集成的 MCP 服务器

UrbanKit County Parcel Atlas

Query verified parcel ArcGIS REST endpoints for 150+ US counties across all 50 states — search by owner name, APN, or address. No API key; built on public county GIS data.

CEIS (Inidôneas e Suspensas)

Enables checking if a person or company appears in the Brazilian CEIS registry using CPF or CNPJ. It's a hosted, read-only MCP server that works with any MCP client.

Google News MCP

Enables AI assistants to fetch real-time news from Google News RSS feeds with support for headlines, categories, location-based queries, and advanced search operators. Features automatic URL decoding, concurrent processing, and intelligent caching for optimized access to global news content.

Commonality MCP Server

MCP-native sales intelligence server enabling prospect enrichment, LinkedIn scraping, and CRM push to HubSpot/Salesforce via natural language.

Tableau MCP Server

Connects Claude Desktop to Tableau Server for natural language interactions with Tableau data, enabling data extraction, dashboard exports, and comprehensive administrative capabilities including user management, permission auditing, and usage analytics.

cowork-media-mcp

Lets Claude Cowork/Desktop generate images via Gemini Flash Image and videos via Google Veo through plain language requests.

MCPGuard

A security gateway that enforces policies, tracks data taints, and sandboxes tool calls between AI agents and MCP servers. It provides a secure chokepoint to prevent prompt injection and ensure OWASP ASI compliance through audit logging and deterministic execution.

Keboola Explorer MCP Server

这个服务器方便与 Keboola Storage API 交互，使用户能够通过 Claude Desktop 高效地浏览和管理项目存储桶、表和组件。

ClinicalTrials.gov MCP Server

Enables searching and retrieving information from the ClinicalTrials.gov database of over 400,000 clinical studies, including trial details, eligibility criteria, locations, and results across 220+ countries.

tradingprogpt

Read-only MCP server exposing MetaTrader 5 account and market data alongside Twelve Data quotes and technical indicators, with an LLM analysis layer.

pages-mcp

Enables uploading and serving static websites via MCP tools, with automatic path prefix injection for multi-file sites.

shopify-mcp

Okay, here's a translation of "for Shopify API interaction including product, customer, order" into Chinese, along with some nuances and options depending on the specific context: **Option 1 (Most General):** * **中文:** 用于 Shopify API 交互，包括产品、客户和订单。 * **Pinyin:** Yòng yú Shopify API jiāohù, bāokuò chǎnpǐn, kèhù hé dìngdān. * **Explanation:** This is a straightforward and common translation. It's suitable for general documentation or explanations. **Option 2 (More Emphasis on "Handling" or "Working With"):** * **中文:** 用于 Shopify API 交互，处理产品、客户和订单。 * **Pinyin:** Yòng yú Shopify API jiāohù, chǔlǐ chǎnpǐn, kèhù hé dìngdān. * **Explanation:** The word "处理 (chǔlǐ)" means "to handle," "to process," or "to deal with." This option is better if you want to emphasize the actions you're taking with the data. **Option 3 (More Technical, Emphasizing Data Manipulation):** * **中文:** 用于 Shopify API 交互，涉及产品、客户和订单的数据操作。 * **Pinyin:** Yòng yú Shopify API jiāohù, shèjí chǎnpǐn, kèhù hé dìngdān de shùjù cāozuò. * **Explanation:** This is a more technical translation. "涉及 (shèjí)" means "involving" or "relating to," and "数据操作 (shùjù cāozuò)" means "data manipulation." This is suitable for technical documentation or code comments. **Option 4 (More Specific to Development):** * **中文:** 用于 Shopify API 交互，开发产品、客户和订单相关功能。 * **Pinyin:** Yòng yú Shopify API jiāohù, kāifā chǎnpǐn, kèhù hé dìngdān xiāngguān gōngnéng. * **Explanation:** This option is suitable if you are talking about developing features related to product, customer and order. "开发 (kāifā)" means "to develop", and "相关功能 (xiāngguān gōngnéng)" means "related features". **Key Vocabulary:** * **Shopify API:** Shopify API (No translation needed, commonly used as is) * **交互 (jiāohù):** Interaction * **产品 (chǎnpǐn):** Product * **客户 (kèhù):** Customer * **订单 (dìngdān):** Order * **用于 (yòng yú):** Used for * **包括 (bāokuò):** Including * **处理 (chǔlǐ):** To handle, to process, to deal with * **涉及 (shèjí):** Involving, relating to * **数据操作 (shùjù cāozuò):** Data manipulation * **开发 (kāifā):** To develop * **相关功能 (xiāngguān gōngnéng):** Related features **Which option is best?** The best option depends on the context. If you're writing general documentation, Option 1 is a good choice. If you're describing the actions you're taking, Option 2 is better. If you're writing technical documentation, Option 3 might be more appropriate. If you are talking about development, Option 4 is a good choice. I hope this helps! Let me know if you have any other questions.

MCP Memory Server

Enables AI assistants to store and retrieve long-term memories with semantic search, supporting various memory types and tags via PostgreSQL and pgvector.

Slovak Law MCP Server

Enables querying and analyzing Slovak legislation via natural language, including full-text search, provision retrieval, and EU law integration.

skill-retrieval-mcp

Enables AI agents to search and retrieve over 89K skills on-demand at runtime, eliminating the need to manually install skills upfront.

MCP Arena

A multiplayer game engine where AI agents connect via Model Context Protocol to compete in real-time strategy games, starting with Chess Royale.

PokeAPI MCP Server

A Model Context Protocol server that interfaces with PokeAPI to provide Pokémon information to LLM applications through JSON-RPC over stdio.

CrewAI Enterprise MCP Server

Enables kicking off deployed CrewAI workflows and inspecting their status and results.

OmniFocus MCP Plus

A comprehensive MCP server for OmniFocus 4 on macOS featuring 34 tools for task management, project organization, and advanced filtering. It enables full CRUD operations for tasks, projects, folders, and tags while supporting custom perspectives and complex repetition rules.

Muninn

A local-first persistent memory server that provides AI agents with deterministic, multimodal information retrieval across different sessions and projects. It enables long-term memory continuity using a 5-signal hybrid search engine and cognitive reasoning loops designed for complex development workflows.