What is 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.
Data-security signals
Public, checkable facts about mcp_excalidraw — they show the risk surface, not what it does with your data at runtime.
- ✓Open-source — the MIT-licensed code is publicly auditable on its public repository.
- ▲High access surface — as an MCP server, it can run with your keys, files, environment and network.
- •Maintenance — actively published.
- ✓Independent exfiltration test — Oxavion tested it and observed no data exfiltration.
✓ Oxavion tested mcp_excalidraw — no exfiltration observed
In Oxavion's sandbox, mcp_excalidraw did not exfiltrate any planted secret or customer data on any monitored channel (HTTP/S, DNS, raw TCP), scoped to the version tested. Want the full evidence report for the version you run?
✓ Request received — we'll run the scan and email your report shortly.
How to tell if mcp_excalidraw is safe
Before you trust any AI tool with your environment, check:
- Is the source auditable? Yes — open-source, you can read it.
- Does it need your keys or credentials? Most mcp servers do — so it holds them at runtime.
- Does it make outbound network calls, and where to? The repo hints at this; only a run confirms it.
- Has it been tested for data exfiltration? Yes — Oxavion observed none.
The first three you can check from the repo yourself. The last — what it does with your data at runtime — needs a test. That is exactly what an Oxavion scan does →
Frequently asked
- Is mcp_excalidraw safe to use?
- It depends on what it does with your data at runtime — something a static look can't settle. Oxavion answers it empirically: we sandbox mcp_excalidraw, feed it canary secrets and data, and report exactly what (if anything) leaves. Request a free scan for a verdict on the version you run.
- How does Oxavion test it?
- An isolated gVisor micro-VM, a transparent egress gateway that captures HTTP/S, DNS and raw TCP, planted canary secrets/PII, and encoding-aware detection — aligned to OWASP LLM Top 10 and MITRE ATLAS, calibrated to zero false-negatives / zero false-positives.