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

11 个服务器

排序方式
Datadog MCP ServerDatadog

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.

2.8k
Grafana MCP ServerGrafana Labs

MCP server for Grafana's observability platform. Enables AI agents to query metrics from Prometheus, search and analyze logs from Loki, query traces, list and manage dashboards, and investigate incidents. Useful for debugging production issues, building monitoring dashboards, and performing root cause analysis with AI assistance across the full Grafana LGTM stack.

2.1k
Apache SkyWalking MCP ServerApache SkyWalking

Apache SkyWalking's MCP server gives agents access to observability data for tracing, service topology, metrics, logs, and production incident investigation.

0
Prometheus MCP ServerPavel Shklovsky

MCP server that lets AI assistants query and analyze Prometheus metrics through standardized interfaces. Exposes instant and range PromQL queries, metric and label discovery, and target/health inspection, allowing agents to investigate system performance and troubleshoot incidents using natural language instead of hand-writing PromQL.

0
SonarQube MCP ServerSonarSource

Official SonarQube MCP server that brings code quality and security analysis into AI workflows. Lets agents fetch project issues, security hotspots, quality-gate status, and metrics from SonarQube Server or SonarCloud, so code health can be inspected and triaged conversationally.

360
DigitalOcean MCP ServerDigitalOcean

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.

300
Dynatrace MCP ServerDynatrace

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.

0
Google Analytics MCP ServerGoogle Analytics

Google's official MCP server for Google Analytics 4. Lets AI agents run reports against the GA4 Data API, discover dimensions and metrics, and explore account and property metadata with server-side aggregation and safe defaults. Runs locally (via pipx) and connects to MCP-compatible clients for conversational analysis of website traffic and user behavior.

0
GrowthBook MCP ServerGrowthBook

GrowthBook's official MCP server for working with feature flags, experiments, and metrics so agents can safely support product experimentation workflows.

0
Render MCP ServerRender

Render's official MCP server for interacting with your Render cloud resources via LLMs. Lets agents list and inspect services, create and manage deploys, read logs and metrics, and query managed Postgres and Key Value instances. Useful for deploying, debugging, and monitoring applications hosted on Render directly from an MCP-compatible assistant.

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