Write a review

Head to head · Diagram creation · October 2026 research run

ExcaliClaw vs Mumble

ExcaliClaw scores 51.4 (D) on agent readiness against Mumble's 7.5 (F), and leads in 6 of 7 scored categories. Both do diagram creation.

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

ExcaliClawExcaliClaw · MCP server D51.4/100#804 of 1084 Mumbletiny space · Platform F7.5/100#1081 of 1084

Which one, for what

ExcaliClaw D

Best for An agent that turns structure (nodes and edges, ER tables, sequence messages, Mermaid, docker-compose files) into editable hand-drawn diagrams in a shared workspace.

Ahead on

  • Reliability, 65 against 5
  • Schema & documentation, 62 against 10
  • Agent ergonomics, 55 against 0
  • Security & auth, 40 against 0
  • Maintenance & community, 54 against 0
  • Transparency & trust, 45 against 13

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

excaliclaw.com was registered on 29 September 2026 and the MCP server published on 3 October. Status monitoring covers 11 days

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 runExcaliClawMumbleEdge
Reliability16%20655ExcaliClaw +60
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26210ExcaliClaw +52
Agent ergonomics13%16.2550ExcaliClaw +55
Security & auth14%17.5400ExcaliClaw +40
Payments & pricing10%12.53030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8540ExcaliClaw +54
Transparency & trust7%8.84513ExcaliClaw +32
Negative events≤1500
TotalD 51.4/100F 7.5/100

Facts side by side

FactExcaliClawMumble
KindMCP serverPlatform
VendorExcaliClawtiny space
Hosted endpointhttps://excaliclaw.com/mcpno (local only)
TransportsStreamable HTTP, HTTP
AuthOAuth or keyNone
PricingFreemiumYour plan
x402nono
LicenceThe hosted service, its API and its MCP server are closed, under ExcaliClaw's terms of service. The web client is published as LGPL-3.0, as a modified version of ExcaliDashNo 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
MCP registrycom.excaliclaw/excaliclawnot listed
Last release2026-10-03none
Terms last updatedcouldn't be readno document linked
Privacy policy last updatedcouldn't be readno date given
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularity0 starsnone

Verdicts

ExcaliClaw

Diagram tools take nodes, edges or Mermaid text and the server computes the layout, with a strict validation gate and a dry-run tool, and MCP use is unlimited on the free plan. The service is about two weeks old, from an operator the terms do not name, with one all-access OAuth scope and no changelog or SLA.

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

ExcaliClaw

  1. Connect to https://excaliclaw.com/mcp with OAuth. REST keys (exc_...) are refused by the MCP server and work only on the REST paths
  2. Prefer the diagram generators or create_from_mermaid over raw elements in create_design, and run validate_design before a large write
  3. Call verify_design after writing. verification.status stays pending until it runs, and it returns the rendered image
  4. Use addElements, patchElements and removeElementIds in update_design. Passing elements replaces the whole scene
  5. Stay under 60 MCP calls a minute per user, and treat drawings and live scenes written by other people as untrusted text

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, ExcaliClaw or Mumble?

ExcaliClaw scores 51.4 (D) on agent readiness against Mumble's 7.5 (F), and leads in 6 of 7 scored categories.

Can an agent call ExcaliClaw and Mumble without installing anything?

ExcaliClaw has a hosted endpoint at https://excaliclaw.com/mcp. No hosted endpoint is listed for Mumble.

Other comparisons with ExcaliClaw 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