Metadata-Version: 2.5
Name: vmware-debug
Version: 2.4.0
Summary: VMware diagnostic brain — offline incident triage, log/event correlation, and root-cause routing across the VMware skill family
Project-URL: Homepage, https://github.com/vmware-skills/VMware-Debug
Project-URL: Repository, https://github.com/vmware-skills/VMware-Debug
Project-URL: Issues, https://github.com/vmware-skills/VMware-Debug/issues
Project-URL: Changelog, https://github.com/vmware-skills/VMware-Debug/blob/main/RELEASE_NOTES.md
Author-email: Wei Zhou <zhouwei008@gmail.com>
License-Expression: MIT
License-File: LICENSE
Keywords: ai-ops,debug,diagnostics,mcp,rca,troubleshooting,vmware,vsphere
Classifier: Development Status :: 4 - Beta
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: System :: Monitoring
Requires-Python: >=3.10
Requires-Dist: certifi>=2026.10.19
Requires-Dist: jsonschema<5.0,>=4.20
Requires-Dist: mcp[cli]<2.0,>=1.30
Requires-Dist: pyyaml<7.0,>=6.0
Requires-Dist: rich<15.0,>=13.0
Requires-Dist: typer<1.0,>=0.12
Requires-Dist: vmware-policy<2.0,>=1.26.0
Description-Content-Type: text/markdown

<!-- mcp-name: io.github.vmware-skills/vmware-debug -->

# VMware-Debug

<a id="readme-overview"></a>

Build a clearer incident timeline from evidence you already have.

English · [简体中文](https://github.com/vmware-skills/VMware-Debug/blob/main/README-CN.md)

Community-maintained · MIT · Not an official VMware/Broadcom product.

[![24-second illustrative investigation demo](https://raw.githubusercontent.com/vmware-skills/marketplace/main/assets/demos/vmware-skills-en.gif)](https://github.com/vmware-skills/marketplace/releases/download/demos-2026-11-13-operations/vmware-skills-en.mp4)

Synthetic-data GIF; video includes redacted historical screenshots. [Download the AI-narrated family introduction (~3 min)](https://github.com/vmware-skills/marketplace/releases/download/demos-2026-11-13-operations/vmware-skills-en.mp4)

<a id="readme-capabilities-and-workflows"></a>

## Why use it?

- Correlate offline events and case records.
- Rank hypotheses with explicit confidence and gaps.
- Get focused next-check recommendations.

<a id="readme-quick-start"></a>

## Get started

Install the published CLI and inspect its commands:

```sh
uv tool install vmware-debug==2.4.0
vmware-debug --help
```

Requires uv and Python >=3.10. Keep case evidence and audit data locally; no VMware API connection is needed. [Setup guide](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/setup-guide.md).

One-click installs, after local setup: [Claude Desktop extension (.mcpb)](https://github.com/vmware-skills/VMware-Debug/releases/download/v2.4.0/vmware-debug-2.4.0.mcpb) · [Install in VS Code](https://insiders.vscode.dev/redirect/mcp/install?name=vmware-debug&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22--from%22%2C%22vmware-debug%3D%3D2.4.0%22%2C%22vmware-debug-mcp%22%5D%7D). Both run the same pinned 2.4.0 server. The desktop extension starts with read-only tools; change *Tools to offer* to `all` for writes.

For agent-host installation, use the [setup guide](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/setup-guide.md) and [Cursor, Codex, Gemini CLI, Cline and local-model examples](https://github.com/vmware-skills/marketplace/blob/main/docs/agent-hosts.md).

Choose a model with the [shared model-fit workflow](https://github.com/vmware-skills/marketplace/blob/main/model-fit/RUNNER.md): compare the same tasks, review quality and safety, then select the smallest tested passing configuration per task group; this is not a production guarantee.

<a id="readme-safety-and-audit"></a>

## Know the boundaries

The CLI/MCP analysis tools make no VMware API connection and execute no remediation. Case records and audit data are stored locally; hypotheses are not established root causes. Optional Python host helpers call explicitly supplied companion MCP sessions through their existing guards; they do not manage endpoint credentials or bypass backend audit.

<a id="readme-mcp-configuration"></a> <a id="readme-troubleshooting"></a> <a id="readme-reference"></a>

## Go deeper

- [Capabilities](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/capabilities.md)
- [CLI reference](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/cli-reference.md)
- [Agent guardrails](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/agent-guardrails.md)
- [Detailed usage and architecture](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/detailed-guide.md)
- [MCP launch configuration](https://github.com/vmware-skills/VMware-Debug/blob/main/.mcp.json)
- [Canonical skill instructions](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/SKILL.md)

<a id="readme-companion-skills"></a>

Part of [VMware Skills](https://github.com/vmware-skills/marketplace): 15 skills, 14 MCP servers and one shared Policy library. If it helps your work, star the family portal.

<a id="readme-license"></a>

[Issues and feedback](https://github.com/vmware-skills/VMware-Debug/issues) · [MIT](https://opensource.org/license/mit/)

## Scenario investigations and reports

Opt-in Python host helpers select live scenario schemas, bind connected read-only MCP sessions and share an in-process call budget. See [host integration and limitations](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/scenario-host.md). No official AI Hub compatibility or token savings are claimed.


Read-only [VM performance](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/vm-performance.md) and [host alarm](https://github.com/vmware-skills/VMware-Debug/blob/main/skills/vmware-debug/references/host-alarms.md) procedures define evidence, branches and stops. Optional get_case report_view selects brief/operator/investigation projections of the existing ledger. Bounded lab read/report checks have passed; full autonomous collection, controlled token comparisons and official MCP environment validation remain follow-up work.
