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

26 个服务器

排序方式
Dropbox MCP ServerDropbox

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.

260
Confluent MCP ServerConfluent

Confluent's open-source MCP server that connects AI assistants to Confluent Cloud, Confluent Platform, and standalone Apache Kafka deployments. Provides tools to manage Kafka topics and connectors, work with Schema Registry, and run Flink SQL statements through natural language, helping teams operate streaming data platforms from an MCP client.

0
E2B MCP ServerE2B

E2B's MCP server gives AI agents the ability to run arbitrary code in secure, isolated cloud sandboxes. Each sandbox is a fast-booting micro-VM where models can execute Python and shell commands, install packages, read and write files, and capture stdout/stderr — ideal for code interpretation, data analysis, and agentic workflows that need real execution.

0
Google Security MCPGoogle

Google's official collection of Model Context Protocol servers that expose Google's security products to MCP clients. Provides access to Google SecOps (Chronicle) for SIEM search and case management, Google Threat Intelligence for indicator and malware lookups, and Security Command Center for cloud posture and findings. Lets security agents investigate alerts, enrich indicators of compromise, and triage vulnerabilities directly from natural language.

0
MotherDuck MCP ServerMotherDuck

Official MCP server for DuckDB and MotherDuck. Lets AI assistants run SQL analytics directly against local DuckDB files, in-memory databases, S3-hosted data, and MotherDuck cloud warehouses. Supports read and write queries, browsing database catalogs, and switching between connections on the fly, making it well suited for conversational data exploration and lightweight analytics.

0

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。

提交到 GitHub