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
Connects AI agents to Datadog for monitoring, observability, and incident management. Enables querying metrics, viewing traces, searching logs, and managing monitors programmatically. Supports dashboard creation, alert configuration, and SLO tracking through the Model Context Protocol.
Prefect's MCP integration gives agents access to orchestration objects including flows, deployments, work pools, and run diagnostics.
MCP server for Sentry error tracking integration. Enables AI agents to retrieve and analyze issues, view error stack traces, search events by query, and access project performance data. Helps developers debug production errors by providing contextual error information directly in AI-powered development workflows.
Apache SkyWalking's MCP server gives agents access to observability data for tracing, service topology, metrics, logs, and production incident investigation.
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.
Dagster's MCP integration enables agents to inspect and operate data assets, jobs, schedules, and runs in modern data platforms.
Dynatrace's official MCP server that brings the Dynatrace observability platform into AI workflows. Lets assistants query problems and vulnerabilities, run DQL against logs, metrics, and traces, inspect entities, and pull real-time monitoring data directly into a developer's coding environment for faster troubleshooting and root-cause analysis.
Honeycomb's MCP server that lets AI assistants query and analyze observability data, including events, traces, alerts (triggers), and boards. Agents can run queries against datasets, inspect columns and schemas, and cross-reference production behavior with the codebase to investigate incidents. Connects to Honeycomb via API key or OAuth.
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。