mcp_excalidraw
MCP server and Claude Code skill for Excalidraw, programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
Runssource: GitHubhomepageTypeScriptMITcommit 713706e967ed
TypeScript, MIT licensed.
mcp_excalidraw runs. An Argusic agent installed it in 26 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Backend TypeScript compiles, npm test suite (MCP wire protocol + canvas bind checks) passes 7/7 checks, canvas server runs serving REST API on :3000, CLI commands (add, describe, export, status) all function correctly creating/managing Excalidraw elements.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Frontend vite build OOM-killed during rendering chunks phase (needs >1.5GB RAM, only 2GB avail with no swap)10 minutes
- Node.js version 18 too old, required >=202 minutes
- Install time
- 26 minutes
- Cold machine to finish
- 27 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test exited 0 (5 MCP stdio checks + bind check); curl /health returned 200; bin.js add/describe/export all produced correct JSON output with created elements
- Model tokens used
- 77,634
- Exact commit tested
- 713706e967ed
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
- Exported scene is valid Excalidraw v2 JSON with bound text elements and arrows **Known limitation (documented in errors):** The Vite frontend build OOMs on 2GB RAM during "render… tokens used 77,634 The ARGUSIC_RESULT line has been printed above. Here's a summary of the work done: **Installation:** Completed successfully after fixing the Node.js version requirement (18 → 20). De… **Verification:** Real end-to-end testing passed: - `npm test` — all 7 checks passed (5 MCP wire protocol + 2 canvas bind) - Canvas server — served healthy REST API on `:3000` - CLI commands — `add`, `describe`, `export`, `status` all produced valid output with actual elemen… - Exported scene is valid Excalidraw v2 JSON with bound text elements and arrows **Known limitation (documented in errors):** The Vite frontend build OOMs on 2GB RAM during "render…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 26 minutes to install, slower than the median of the 24 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 25 TypeScript projects Argusic has installed and timed, mcp_excalidraw was the 25th fastest to reach a running state, and 19 of 25 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Run history
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-excalidraw)Questions
- Does mcp_excalidraw run?
- Yes. mcp_excalidraw runs. Argusic installed and launched it on a clean machine in 26 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test mcp_excalidraw?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 713706e967ed. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp_excalidraw?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp_excalidraw take to install?
- 26 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does mcp_excalidraw need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp_excalidraw?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does mcp_excalidraw compare with the alternatives?
- Of the 25 TypeScript projects Argusic has installed and timed, mcp_excalidraw was the 25th fastest to reach a running state, and 19 of 25 reached one at all.
- Where is the evidence for mcp_excalidraw?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.