docs: add vmware-aiops MCP extension documentation#8055
Conversation
Signed-off-by: Wei Zhou <zw008@github.com>
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 6c8018b071
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| name="vmware-aiops" | ||
| description="Natural language VMware vCenter/ESXi monitoring and operations" | ||
| type="stdio" | ||
| command="python -m mcp_server" |
There was a problem hiding this comment.
The setup tells users to run uv tool install vmware-aiops and then configure goose with python -m mcp_server, but uv tool install installs package commands in an isolated tool environment rather than into the default Python import path. In that flow, goose will invoke the system python, which typically cannot import mcp_server, so the extension fails to start (e.g., ModuleNotFoundError). Please switch the configured command to the installed tool entrypoint (vmware-aiops ... or uvx vmware-aiops ...), and mirror that in the Desktop block as well.
Useful? React with 👍 / 👎.
The package exposes a dedicated 'vmware-aiops-mcp' script entry point. Using 'python -m mcp_server' would fail with ModuleNotFoundError since uv tool install places the package in an isolated environment. Replace both Desktop and CLI command configs with: uvx --from vmware-aiops vmware-aiops-mcp Signed-off-by: Douwe Osinga <douwe@squareup.com>
DOsinga
left a comment
DOsinga
left a comment
There was a problem hiding this comment.
The command configuration was using python -m mcp_server which would fail with ModuleNotFoundError since uv tool install places the package in an isolated environment. Fixed both the Desktop and CLI configs to use the dedicated vmware-aiops-mcp script entry point via uvx --from vmware-aiops vmware-aiops-mcp.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1dade11afd
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| Install vmware-aiops first: | ||
| ```sh | ||
| uv tool install vmware-aiops | ||
| vmware-aiops mcp-config install --agent goose |
There was a problem hiding this comment.
The Quick Install step uses vmware-aiops mcp-config install --agent goose right after uv tool install vmware-aiops, but in that installation mode the generated goose config is not aligned with this page’s working uvx --from vmware-aiops vmware-aiops-mcp setup and can fail at runtime when goose launches the server (commonly as python -m mcp_server import/cwd issues). Fresh evidence: upstream vmware_aiops/cli.py still has mcp_config_install writing the agent template from examples/mcp-configs/goose.json, which uses the Python-module form rather than the uvx command shown later here. This means users following the advertised “Quick Install” path can end up with a non-starting extension.
Useful? React with 👍 / 👎.
* origin/main: (62 commits) Tweak the release process: no more merge to main (#7994) fix: gemini models via databricks (#8042) feat(apps): Pass toolInfo to MCP Apps via hostContext (#7506) fix: remove configured marker when deleting oauth provider configuration (#7887) docs: add vmware-aiops MCP extension documentation (#8055) Show setup instructions for ACP providers in settings modal (#8065) deps: replace sigstore-verification with sigstore-verify to kill vulns (#8064) feat(acp): add session/set_config and stabilize list, delete and close (#7984) docs: Correct `gosoe` typo to `goose` (#8062) fix: use default provider and model when provider in session no longer exists (#8035) feat: add GOOSE_SHELL env var to configure preferred shell (#7909) fix(desktop): fullscreen header bar + always-visible close controls (#8033) docs: add Claude Code approve mode permission routing documentation (#7949) chatgpt_codex: Support reasoning and gpt-5.4 (#7941) refactor(anthropic): fix N+1 thinking message storage issue (#7958) fix: handle mid-stream error events in OpenAI SSE streaming (#8031) Fix apps extension: coerce string arguments from inner LLM responses (#8030) feat: ability to expand sidebar to see chats names (#7816) Fix config for GOOSE_MAX_BACKGROUND_TASKS (#7940) set MACOSX_DEPLOYMENT_TARGET=12.0 (#7947) ...
…pstream * wpfleger/socket-support: (62 commits) Tweak the release process: no more merge to main (#7994) fix: gemini models via databricks (#8042) feat(apps): Pass toolInfo to MCP Apps via hostContext (#7506) fix: remove configured marker when deleting oauth provider configuration (#7887) docs: add vmware-aiops MCP extension documentation (#8055) Show setup instructions for ACP providers in settings modal (#8065) deps: replace sigstore-verification with sigstore-verify to kill vulns (#8064) feat(acp): add session/set_config and stabilize list, delete and close (#7984) docs: Correct `gosoe` typo to `goose` (#8062) fix: use default provider and model when provider in session no longer exists (#8035) feat: add GOOSE_SHELL env var to configure preferred shell (#7909) fix(desktop): fullscreen header bar + always-visible close controls (#8033) docs: add Claude Code approve mode permission routing documentation (#7949) chatgpt_codex: Support reasoning and gpt-5.4 (#7941) refactor(anthropic): fix N+1 thinking message storage issue (#7958) fix: handle mid-stream error events in OpenAI SSE streaming (#8031) Fix apps extension: coerce string arguments from inner LLM responses (#8030) feat: ability to expand sidebar to see chats names (#7816) Fix config for GOOSE_MAX_BACKGROUND_TASKS (#7940) set MACOSX_DEPLOYMENT_TARGET=12.0 (#7947) ...
2 participants
Summary
Adds documentation for vmware-aiops, an MCP server that enables natural language management of VMware vCenter/ESXi infrastructure via goose.
What it does:
Install:
Checklist:
_template_.mdxstructure (frontmatter, Quick Install, Configuration with tabs, Example Usage)git commit -s)vmware-aiops-mcp.mdfollowing existing conventionSigned-off-by: Wei Zhou zw008@github.com