# Mumble vs PlantUML

> PlantUML scores 66.9 (B) to Mumble's 7.5 (F) for diagram creation. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/mumble-vs-plantuml
- Markdown: https://www.anchorterminal.com/compare/mumble-vs-plantuml.md (~2,550 tokens)
- Slim: https://www.anchorterminal.com/compare/mumble-vs-plantuml.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/mumble-vs-plantuml.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-14

PlantUML scores 66.9 (B) on agent readiness against Mumble's 7.5 (F), and leads in every scored category. Both do diagram creation.

- Mumble: grade F, 7.5/100, rank #1081 of 1084. Markdown https://www.anchorterminal.com/tools/mumble.md · JSON https://www.anchorterminal.com/api/v1/tools/mumble.json
- PlantUML: grade B, 66.9/100, rank #286 of 1084. Markdown https://www.anchorterminal.com/tools/plantuml.md · JSON https://www.anchorterminal.com/api/v1/tools/plantuml.json
- Best diagramming APIs and diagram-as-code for AI agents: https://www.anchorterminal.com/best/diagramming/index.md
- All 128 diagrams comparisons: https://www.anchorterminal.com/compare/diagramming/index.md

## Which one, for what

### Mumble (F)

Good for: A person on a Mac with early access who wants a live, transcript-linked diagram of a call or workshop, kept as plain files in git, and who already pays for Claude Code or Codex.

Watch for: No API or MCP server an outside agent can call. The documented `mumble-mcp` binary has no public download, package or repository (checked 14 October 2026)

### PlantUML (B)

Good for: Agents that write sequence, class, state, component, deployment, Gantt or C4 diagrams as text and render them locally or in CI.

Ahead on:
- Reliability, 83 against 5
- Schema & documentation, 65 against 10
- Agent ergonomics, 78 against 0
- Security & auth, 50 against 0
- Payments & pricing, 60 against 30
- Maintenance & community, 73 against 0
- Transparency & trust, 73 against 13

Also in its favour:
- Open source

Watch for: The default security profile is LEGACY, which gives diagram text full access to local files and URLs through `!include`. The docs say it will be removed, with no date


## Score by category

| Category | Weight | Mumble | PlantUML | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 5 | 83 | PlantUML +78 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 10 | 65 | PlantUML +55 |
| Agent ergonomics | 13% (16.2 this run) | 0 | 78 | PlantUML +78 |
| Security & auth | 14% (17.5 this run) | 0 | 50 | PlantUML +50 |
| Payments & pricing | 10% (12.5 this run) | 30 | 60 | PlantUML +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 0 | 73 | PlantUML +73 |
| Transparency & trust | 7% (8.8 this run) | 13 | 73 | PlantUML +60 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **7.5 · F** | **66.9 · B** | |

## Facts side by side

| Fact | Mumble | PlantUML |
| --- | --- | --- |
| Kind | Platform | SDK + MCP |
| Vendor | tiny space | PlantUML project (Arnaud Roques) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Your plan | Free |
| x402 | no | no |
| Licence | No licence, terms of use or source repository was found on tinyspace.ai or GitHub (checked 2026-10-14). The app and the `mumble-mcp` binary are not published as open source | GPL-3.0-or-later |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | none | 2026-09-05 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | none | 13k stars, 207 npm/wk |

## Verdicts

**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.

**PlantUML.** One Java command reads diagram text from stdin and writes PNG, SVG, PDF or ASCII with no account, and CI passed on the last eight pushes. The default security profile lets diagram text read any local file and fetch any URL, and the documentation still lists chronology diagrams that release 1.2026.2 switched off.

## Before you call either

### 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

### PlantUML

1. Set `PLANTUML_SECURITY_PROFILE` to `SANDBOX` or `ALLOWLIST` before rendering text from an untrusted source. The default profile lets `!include` read local files and fetch URLs
2. Run `java -jar plantuml.jar --check-syntax` with `-stdrpt` first and read the exit status. Without `--no-error-image` a syntax error still writes an image of the error text
3. Pass `-pipe` with `--svg`, `--txt` or `--utxt` to work without files. `--txt` output suits a text-only model
4. Start the local server as `-picoweb:8080:127.0.0.1`. Without the bind address it listens on every interface
5. Use `npx -y @plantuml/mcp-js` when no Java runtime is present. It renders SVG only, so use the jar for PNG or PDF

## Questions

### Which is better for AI agents, Mumble or PlantUML?

PlantUML scores 66.9 (B) on agent readiness against Mumble's 7.5 (F), and leads in every scored category.

### Are Mumble and PlantUML open source?

No open-source release is listed for Mumble. PlantUML is open source (GPL-3.0-or-later).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/mumble-vs-plantuml.json, and with the fewest tokens: https://www.anchorterminal.com/compare/mumble-vs-plantuml.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "mumble", "b": "plantuml"}`. From a terminal: `anchor compare mumble plantuml`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/mumble.json and https://www.anchorterminal.com/api/v1/tools/plantuml.json

## Other comparisons with Mumble or PlantUML

- [Cloudviz API vs Mumble](https://www.anchorterminal.com/compare/cloudviz-vs-mumble.md)
- [Cloudviz API vs PlantUML](https://www.anchorterminal.com/compare/cloudviz-vs-plantuml.md)
- [D2 vs Mumble](https://www.anchorterminal.com/compare/d2-vs-mumble.md)
- [Diagrams.so API + MCP vs Mumble](https://www.anchorterminal.com/compare/diagrams-so-vs-mumble.md)
- [Diagrams.so API + MCP vs PlantUML](https://www.anchorterminal.com/compare/diagrams-so-vs-plantuml.md)
- [draw.io + MCP vs Mumble](https://www.anchorterminal.com/compare/drawio-vs-mumble.md)
- [draw.io + MCP vs PlantUML](https://www.anchorterminal.com/compare/drawio-vs-plantuml.md)
- [Eraser API + MCP vs Mumble](https://www.anchorterminal.com/compare/eraser-vs-mumble.md)
- [Eraser API + MCP vs PlantUML](https://www.anchorterminal.com/compare/eraser-vs-plantuml.md)
- [ExcaliClaw vs Mumble](https://www.anchorterminal.com/compare/excaliclaw-vs-mumble.md)
- [ExcaliClaw vs PlantUML](https://www.anchorterminal.com/compare/excaliclaw-vs-plantuml.md)
- [Excalidraw vs Mumble](https://www.anchorterminal.com/compare/excalidraw-vs-mumble.md)
- [Excalidraw vs PlantUML](https://www.anchorterminal.com/compare/excalidraw-vs-plantuml.md)
- [Kroki vs Mumble](https://www.anchorterminal.com/compare/kroki-vs-mumble.md)
- [Lucid API + MCP vs Mumble](https://www.anchorterminal.com/compare/lucid-vs-mumble.md)
- [Lucid API + MCP vs PlantUML](https://www.anchorterminal.com/compare/lucid-vs-plantuml.md)
- [Mermaid Chart MCP vs Mumble](https://www.anchorterminal.com/compare/mermaid-chart-vs-mumble.md)
- [Mermaid Chart MCP vs PlantUML](https://www.anchorterminal.com/compare/mermaid-chart-vs-plantuml.md)
- [Mumble vs Mural MCP](https://www.anchorterminal.com/compare/mumble-vs-mural-mcp.md)
- [Mumble vs Structurizr + MCP](https://www.anchorterminal.com/compare/mumble-vs-structurizr.md)
- [Mumble vs tldraw SDK + MCP](https://www.anchorterminal.com/compare/mumble-vs-tldraw.md)
- [Mumble vs Whimsical MCP](https://www.anchorterminal.com/compare/mumble-vs-whimsical.md)
- [Mural MCP vs PlantUML](https://www.anchorterminal.com/compare/mural-mcp-vs-plantuml.md)
- [PlantUML vs Whimsical MCP](https://www.anchorterminal.com/compare/plantuml-vs-whimsical.md)
- [D2 vs PlantUML](https://www.anchorterminal.com/compare/d2-vs-plantuml.md)
- [Kroki vs PlantUML](https://www.anchorterminal.com/compare/kroki-vs-plantuml.md)
- [PlantUML vs Structurizr + MCP](https://www.anchorterminal.com/compare/plantuml-vs-structurizr.md)
- [PlantUML vs tldraw SDK + MCP](https://www.anchorterminal.com/compare/plantuml-vs-tldraw.md)

## Disclosure

- Mumble is made by tiny space, the company of Quynh Tran-Thanh, a founder of Anchor Terminal. It's graded the same way as every listing, by the same published checklist with the same readings, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed. letme never picks it.