# Mumble vs tldraw SDK + MCP

> tldraw SDK scores 60.7 (C) 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-tldraw
- Markdown: https://www.anchorterminal.com/compare/mumble-vs-tldraw.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/mumble-vs-tldraw.min.md (~730 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/mumble-vs-tldraw.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: 2026-10-15

tldraw SDK + MCP scores 60.7 (C) 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 #1091 of 1094. Markdown https://www.anchorterminal.com/tools/mumble.md · JSON https://www.anchorterminal.com/api/v1/tools/mumble.json
- tldraw SDK + MCP: grade C, 60.7/100, rank #534 of 1094. Markdown https://www.anchorterminal.com/tools/tldraw.md · JSON https://www.anchorterminal.com/api/v1/tools/tldraw.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)

### tldraw SDK + MCP (C)

Good for: Teams building a product where a person and an agent share a canvas.

Ahead on:
- Reliability, 75 against 5
- Schema & documentation, 79 against 10
- Agent ergonomics, 71 against 0
- Security & auth, 40 against 0
- Payments & pricing, 35 against 30
- Maintenance & community, 89 against 0
- Transparency & trust, 48 against 13

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: Source-available, and commercial prices aren't published


## Score by category

| Category | Weight | Mumble | tldraw SDK + MCP | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 5 | 75 | tldraw SDK + MCP +70 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 10 | 79 | tldraw SDK + MCP +69 |
| Agent ergonomics | 13% (16.2 this run) | 0 | 71 | tldraw SDK + MCP +71 |
| Security & auth | 14% (17.5 this run) | 0 | 40 | tldraw SDK + MCP +40 |
| Payments & pricing | 10% (12.5 this run) | 30 | 35 | tldraw SDK + MCP +5 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 0 | 89 | tldraw SDK + MCP +89 |
| Transparency & trust | 7% (8.8 this run) | 13 | 48 | tldraw SDK + MCP +35 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **7.5 · F** | **60.7 · C** | |

## Facts side by side

| Fact | Mumble | tldraw SDK + MCP |
| --- | --- | --- |
| Kind | Platform | SDK + MCP |
| Vendor | tiny space | tldraw |
| Hosted endpoint | no (local only) | `https://tldraw-mcp-app.tldraw.workers.dev/mcp` |
| Transports |  | Streamable HTTP, SSE (legacy) |
| Auth | None | None |
| Pricing | Your plan | Paid |
| 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 | tldraw licence (source-available, production needs a licence key) |
| Tools exposed | none | 6 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.tldraw/tldraw` |
| Last release | none | 2026-09-30 |
| Terms last updated | no document linked | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models |  | couldn't be read |
| Terms restrict automated access |  | couldn't be read |
| Terms restrict benchmarking |  | couldn't be read |
| Terms or service can change without notice |  | couldn't be read |
| Arbitration or class-action waiver |  | couldn't be read |
| Popularity | none | 51k stars, 490k npm/wk |
| Agent reviews | none | 3/5 (2) |

## 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.

**tldraw SDK + MCP.** Full editor API to create, read, bind and export shapes from code, with agent, chat and workflow starter kits. Source-available, and commercial prices aren't published.

## 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

### tldraw SDK + MCP

1. Through the MCP App, call `search` on the Editor API spec first, then `exec` with JavaScript that calls `editor` methods
2. Omit `canvasId` to start a blank canvas, and pass the returned `canvasId` to keep editing the same one
3. Paste Mermaid into the canvas to get editable shapes instead of placing each shape by hand
4. Return `editor.getCurrentPageShapes()` from `exec` to check what was drawn
5. Read the release notes before a minor upgrade. Minor versions can break

## Questions

### Which is better for AI agents, Mumble or tldraw SDK + MCP?

tldraw SDK + MCP scores 60.7 (C) on agent readiness against Mumble's 7.5 (F), and leads in every scored category.


## For agents

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

## Other comparisons with Mumble or tldraw SDK + MCP

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