MCP 服务器
开放的 Model Context Protocol 服务器注册表。按类别、传输方式或使用场景,为 AI 智能体寻找合适的工具、资源和提示词。
服务器
177
工具
471
类别
11
贡献者
155
Automattic's MCP server that connects AI assistants such as Claude Desktop to WordPress sites. Supports multiple authentication methods (OAuth 2.0, JWT, and application passwords) and exposes the WordPress REST and WP-CLI capabilities so agents can read and manage posts, pages, media, and site settings through natural language.
Zoom's official remote MCP server, published to the MCP registry, that gives AI agents access to Zoom capabilities over the Model Context Protocol. Supports semantic meeting search, Zoom-wide chat and docs search, meeting assets and recording resources, and Zoom Docs import/export, so assistants can find and summarize meeting content and manage related data. Authenticates via OAuth.
Official Box MCP server for enterprise content management. Lets AI agents search files, read documents, extract text and metadata, ask questions with Box AI, and manage folders via the Box API. Useful for document analysis, knowledge retrieval, and automating content workflows over files stored in Box.
Official Browserbase MCP server for cloud browser automation. Lets AI agents create headless browser sessions, navigate pages, extract content, take screenshots, and perform actions using Stagehand, enabling reliable web automation and scraping at scale from AI-powered tools.
Official CircleCI MCP server. Lets AI agents fetch build and pipeline status, retrieve failed build logs, and diagnose flaky or broken jobs so developers can fix CI failures without leaving their AI-powered tools.
MCP server for the ClickUp project management platform. Enables AI agents to create and update tasks, browse spaces, folders, and lists, and manage task status and assignees, bringing ClickUp work management into AI-powered tools.
MCP server for the Databricks Data Intelligence Platform. Enables AI agents to run SQL against the Unity Catalog, inspect schemas and tables, and manage and monitor jobs, bringing lakehouse data and workflows into AI-powered development tools.
Official dbt Labs MCP server for analytics engineering workflows. Lets AI agents run dbt commands (build, run, test), inspect models and lineage via the dbt project, and query the Semantic Layer and Discovery API in dbt Cloud. Useful for transforming data, validating models, and answering metric questions grounded in governed definitions.
Official DigitalOcean MCP server for managing cloud infrastructure. Lets AI agents deploy and manage App Platform apps, Droplets, databases, and Spaces object storage, and read logs and metrics. Useful for provisioning and operating cloud resources and debugging deployments through an AI assistant.
MCP server for Dropbox cloud storage. Lets AI agents list folders, upload and download files, search content, move and delete items, and create shared links via the Dropbox API with OAuth. Useful for document workflows, backups, and giving agents access to files stored in Dropbox.
MCP server for DuckDB, the fast in-process analytical database. Lets AI agents run analytical SQL over local files (CSV, Parquet, JSON), attach databases, inspect schemas, and profile queries. Ideal for ad-hoc data analysis, ETL prototyping, and querying large columnar files without a separate database server.
Official MCP server for the ElevenLabs audio platform. Gives AI agents text-to-speech, voice cloning, speech-to-text transcription, sound-effect generation, and voice library management. Useful for building voice agents, narration, audiobooks, dubbing, and accessible audio experiences.
MCP server for the Google Maps Platform. Enables AI agents to geocode addresses, search for places, retrieve place details, and compute directions and distances, giving models location awareness and routing from AI-powered tools.
MCP server for Google Sheets. Lets AI agents read and write cell ranges, create and update spreadsheets and tabs, append rows, and apply formatting via the Sheets API with OAuth. Useful for lightweight data entry, reporting, dashboards, and automating spreadsheet-driven workflows.
MCP server for Hacker News. Lets AI agents fetch top, new, best, Ask HN, and Show HN stories, read comment threads, and look up items and users via the official Firebase API. Useful for tracking tech trends, summarizing discussions, and research into what the developer community is talking about.
MCP server for HashiCorp Vault secrets management. Enables AI agents to read and write secrets, list secret paths, and manage key/value engines under controlled policies, so applications and workflows can retrieve credentials securely from AI-powered tools.
MCP server for Intercom. Lets AI agents search and read conversations and contacts, retrieve message history, and query help-center articles via the Intercom API. Useful for support analytics, conversation summarization, and building assistants that reason over customer communications.
MCP server for Jenkins CI/CD. Enables AI agents to trigger builds, inspect job and build status, stream console logs, and diagnose failing pipelines, bringing continuous integration workflows into AI-powered development environments.
MCP server for Langfuse, the open-source LLM observability and prompt management platform. Enables AI agents to fetch and render managed prompts, list prompt versions, and query traces, helping teams manage prompts and inspect LLM application behavior from AI-powered tools.
Official LaunchDarkly MCP server for feature management. Lets AI agents create and toggle feature flags, manage targeting rules and segments, and inspect flag status across environments. Useful for progressive delivery, kill switches, experimentation, and automating flag lifecycle from an AI assistant.
Official MCP server for the Milvus vector database. Lets AI agents create collections, insert vectors, and run similarity and scalar-filtered searches over large-scale embedding data, enabling retrieval and long-term memory for AI applications.
Skills 与 MCP 服务器
有什么区别?Skills定义“做什么”
Skill 将说明、示例提示词和推荐模型组织在一起,让智能体稳定地完成任务。Skills 增加的是知识,而不是新的连接。
MCP 服务器定义“如何连接”
MCP 服务器通过连接数据库、API 和文件等真实系统,为智能体增加新能力。MCP 提供连接和操作,而不是任务说明。
简单来说:当模型需要把某项任务做好时选择 Skill;当模型需要访问工具或系统时选择 MCP 服务器。两者可以组合使用,Skill 可以依赖 MCP 服务器提供的工具。
开发了 MCP 服务器?
将它提交到由社区维护的开源注册表。