Unified observability MCP server: SkyWalking (OAP GraphQL) + Zabbix, with cross-stack correlation.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"skywalking-zabbix-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# skywalking-zabbix-mcp [](https://github.com/ningjiabing/skywalking-zabbix-mcp/actions/workflows/ci.yml) [](https://pypi.org/project/skywalking-zabbix-mcp/) [](https://pypi.org/project/skywalking-zabbix-mcp/) [](LICENSE) 简体中文 | [English](README.en.md) 一个 MCP Server，把 **SkyWalking（应用 APM）** 和 **Zabbix（主机监控）** 接进同一个进程，让 AI 助手能在一次对话里既看应用指标、又看机器指标，并把两者关联起来。 **它解决什么问题？** 排障时你通常要开两个系统：SkyWalking 看服务慢在哪、Zabbix 看机器是不是扛不住了，然后人脑对时间线判断「是机器先炸拖垮了应用，还是应用自己的 bug」。这个 server 把这一步交给 AI——你问一句「payment-service 怎么了」，它自动拉齐应用侧和机器侧两份数据给出结论。 **为什么能自动关联？** SkyWalking 的服务名格式是 `<IP>::<服务名>`（如 `192.0.2.11::payment-service`），其中的 IP 段正好就是 Zabbix 里的主机名。两边天然用 IP 对齐，**不需要维护任何服务↔主机映射表**。 <p align="center"> <img src="docs/demo.svg" alt="diagnose_service 与 correlate_incident 的实际输出" width="100%"> </p> <p align="center"> <sub>真实的 server 代码跑在 <a href="docs/demo/">mock 后端</a> 上，数据为合成数据。用 <code>uv run python docs/demo/run_demo.py</code> 可自行复现。</sub> </p> --- ## 两种运行形态 | 配置 | 得到的 server | |---|---| | 只配 `SW_*` | **纯 SkyWalking**：16 个工具 + 10 prompts + 4 resources | | 加配 `ZABBIX_URL` 等 | **应用 + 机器一体**：上面 16 个 + Zabbix 2 个 + 跨栈关联 2 个 = **20 工具** | 换句话说：**配了 `ZABBIX_URL` 才会注册 Zabbix 和关联相关的 4 个工具**，否则退化为纯 SkyWalking server。 --- ## 快速上手 ### 1. 安装（三选一） **A. uvx —— 不用 clone，一行跑起来（推荐）** ```bash uvx skywalking-zabbix-mcp --version ``` **B. Docker** ```bash docker run --rm -i \ -e SW_URL=http://<oap-host>:12800 \ ghcr.io/ningjiabing/skywalking-zabbix-mcp ``` **C. 源码（要改代码就用这个）** ```bash git clone https://github.com/ningjiabing/skywalking-zabbix-mcp.git cd skywalking-zabbix-mcp uv sync uv run skywalking-zabbix-mcp --version ``` ### 2. 接入 AI 客户端 <details open> <summary><b>Claude Code</b></summar…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.