D2 vs Mumble

D2

A single local command turns text into a diagram in six formats with no account, key or network call, and CI passes on the default branch. The language is at 0.9.0 with no stable release, its company sponsor has shut down, and one maintainer with limited time wrote every commit since July.

Mumble

Mumble keeps audio on the Mac and stores each conversation as plain files in ~/Mumble, with canvas JSON that diffs cleanly. There is no API or MCP server an outside agent can call today. The documented mumble-mcp has no public download, package or repository, and the app is reached only through an early-access waitlist.

D2

1. Check the exit status of d2, never the output file. The man page says a partial render can be written when an error occurs
2. Run d2 validate file.d2 before rendering, and d2 fmt to normalise the source
3. Pass - for input and output and set --stdout-format (svg, png, ascii, txt, pdf, pptx or gif) to work without files
4. Use --stdout-format ascii when the reader is a text-only model
5. Pass --bundle=false or review image URLs and imports before rendering D2 text from an untrusted source. Release 0.9.0 fetches remote images when bundling

Mumble

1. Don't plan to call Mumble from another agent. Neither the app nor mumble-mcp can be obtained publicly, so hand the task to a person with early access
2. Don't configure /path/to/mumble-mcp from the docs. It is a placeholder, and no binary is published
3. If the person already has Mumble, read ~/Mumble/<capture>/ directly, capture.json for the transcript and diagram.canvas for the map
4. Keep canvas keys in schema order and never rename a node id, or the edges that name it are orphaned and the canvas is refused. Use git as the undo
5. Don't write to a capture that is being recorded. The app doesn't merge the two versions