@kamiazya/whiteboard-mcp
npm
v0.0.19
Source verified
Published by kamiazya — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
MCP server + Excalidraw whiteboard UI for AI-assisted diagramming (Claude Code / Codex).
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Hardcoded Google API key in server code MTC-SRC-008 | exfiltration |
2. Client adoption risk — 99 − 6 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
In the server's implementation (`dist/web-app/assets/chunk-EIO257PC-Dt-y2JKs.js:2`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: pt(e,t){return e=ft(e),Function(`body`,`return function ${e}() { "use strict"; return body.apply(this, arguments
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/web-app/assets/chunk-EIO257PC-Dt-y2JKs.js
In the server's implementation (`dist/daemon/ensure-daemon.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { mkdirSync, openSync } from 'node:fs'; import { join } from 'node:path';
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/daemon/ensure-daemon.js
In the server's implementation (`dist/cli/daemon-ping-client.js:26`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`http://${connectHost}:${port}/api/runtime/ping`, { signal: AbortSignal.timeou
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/daemon-ping-client.js
In the server's implementation (`dist/cli/server-doctor.js:98`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`http://${connectHost}:${port}/api/runtime/status`, { signal: AbortSignal.time
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/cli/server-doctor.js
In the server's implementation (`dist/daemon/ensure-daemon.js:87`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const res = await fetch(`http://${host}:${port}/api/runtime/ping`); return res.ok; } catch {
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/daemon/ensure-daemon.js
In the server's implementation (`dist/server/mcp/tools/canvas-inspect.js:26`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: oDoc(); doc.import(bytes); return summarizeCanvas(doc); }, }; } //# sourceMappingURL
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/server/mcp/tools/canvas-inspect.js
In the server's implementation (`dist/server/routes/canvas/live-doc.js:43`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eId, slug); doc.import(bytes); try { await saveCanvas(workspaceId, slug, doc, { overwrite: t
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/server/routes/canvas/live-doc.js
In the server's implementation (`dist/web-app/assets/app-routes-C6xmFr8d.js:971`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: let r = await n(()=>import(e.module).then(async (m)=>{ await m.__tla; return
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/web-app/assets/app-routes-C6xmFr8d.js
In the server's implementation (`dist/web-app/assets/import-browser-local-DJP4aKTB.js:21`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: return new u().import(e), !0; } catch { return !1; } } let h; m = clas
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/web-app/assets/import-browser-local-DJP4aKTB.js
In the server's implementation (`dist/web-app/assets/loro_wasm_bg-DU7zxaV1.js:1299`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: } } import(e) { try { let r = i.__wbindgen_add_to_stack_pointer(-16), a
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/web-app/assets/loro_wasm_bg-DU7zxaV1.js
A hardcoded Google API key (a public Firebase/web API key) appears in `dist/web-app/assets/chunk-ZUYEQ4TG-BzFOpW--.js:1`. Verify whether this is a real credential; if so, remove and rotate it.
Evidence: Google API key: AIza…(redacted)
Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.
Location: server dist/web-app/assets/chunk-ZUYEQ4TG-BzFOpW--.js
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.0.19 latest |
A 93/100 | 11 | 1.13.0 | 2026-09-07 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @kamiazya/whiteboard-mcp --online
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
A web-based whiteboard service
AI-powered whiteboard — draw diagrams, flowcharts, and sketches via MCP tools
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand