Write a review

Head to head · Diagram creation · October 2026 research run

Excalidraw vs Mumble

Excalidraw scores 54.5 (C) on agent readiness against Mumble's 7.5 (F), and leads in every scored category. Both do diagram creation.

Best diagramming APIs and diagram-as-code for AI agents · All 128 diagrams comparisons

ExcalidrawExcalidraw s.r.o. · HTTP API C54.5/100#729 of 1084 Mumbletiny space · Platform F7.5/100#1081 of 1084

Which one, for what

Excalidraw C

Best for Teams already on Excalidraw+ that want agents to create and edit hand-drawn diagrams, slides and wireframes in a shared workspace, and one-off sketches through the free MCP App.

Ahead on

  • Reliability, 50 against 5
  • Schema & documentation, 65 against 10
  • Agent ergonomics, 58 against 0
  • Security & auth, 73 against 0
  • Payments & pricing, 35 against 30
  • Maintenance & community, 44 against 0
  • Transparency & trust, 63 against 13

Also in its favour

  • A hosted endpoint, with nothing to install
  • Open source

Watch for

The API and MCP server are in public beta. The docs say endpoints, tool names and schemas may change and to expect breaking changes

Mumble F

Best 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.

Also in its favour

  • No key needed to call it

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)

Score by category

CategoryWeight this runExcalidrawMumbleEdge
Reliability16%20505Excalidraw +45
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26510Excalidraw +55
Agent ergonomics13%16.2580Excalidraw +58
Security & auth14%17.5730Excalidraw +73
Payments & pricing10%12.53530Excalidraw +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8440Excalidraw +44
Transparency & trust7%8.86313Excalidraw +50
Negative events≤15-20
TotalC 54.5/100F 7.5/100

Facts side by side

FactExcalidrawMumble
KindHTTP APIPlatform
VendorExcalidraw s.r.o.tiny space
Hosted endpointhttps://api.excalidraw.com/api/v1/mcpno (local only)
TransportsHTTP, Streamable HTTP
AuthAPI keyNone
PricingFreemiumYour plan
x402nono
LicenceExcalidraw+ is a proprietary service under Excalidraw's terms of use. The editor and the MCP App on GitHub are MITNo 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
Tools exposed37none
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-01none
Terms last updatedno date givenno document linked
Privacy policy last updated2021-04-29no date given
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity134k stars, 676k npm/wknone

Verdicts

Excalidraw

Excalidraw+ keys carry read or full permission, route restrictions and an expiry, and the MCP server shows a key only the tools its routes allow. The API and MCP server are in public beta with breaking changes expected, sit behind the $6 Plus plan, and have no published OpenAPI file, SDK or idempotency keys.

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.

Before you call either

Excalidraw

  1. Send Authorization: Bearer <API_KEY> to https://api.excalidraw.com/api/v1. For MCP, use POST /api/v1/mcp only. The server is stateless and answers 405 to other methods
  2. Use a personal key to reach the owner's private collection with the collection ID private. A workspace admin must enable personal keys first
  3. Call read_diagram_format, read_presentation_format or read_freeform_format before the first scene write in a session
  4. Write with edit_scene_content and bind arrows through startBinding and endBinding with tempId references. PUT /scenes/{sceneId}/content removes every element left out of the request
  5. Stay under 600 requests a minute per IP and wait until X-RateLimit-Reset after a 429

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

Questions

Which is better for AI agents, Excalidraw or Mumble?

Excalidraw scores 54.5 (C) on agent readiness against Mumble's 7.5 (F), and leads in every scored category.

Can an agent call Excalidraw and Mumble without installing anything?

Excalidraw has a hosted endpoint at https://api.excalidraw.com/api/v1/mcp. No hosted endpoint is listed for Mumble.

Are Excalidraw and Mumble open source?

Excalidraw is open source (Excalidraw+ is a proprietary service under Excalidraw's terms of use. The editor and the MCP App on GitHub are MIT). No open-source release is listed for Mumble.

Other comparisons with Excalidraw or Mumble

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.

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report