eaccmk_excalidraw-mcp: Instructions file for Claude Code

CLAUDE.md

eaccmk_excalidraw-mcp CLAUDE.md is an instructions file for Claude Code from eaccmk/eaccmk_excalidraw-mcp. It costs 2,343 tokens per session, scanned A, original, MIT.

Instructions for an MCP server that creates Excalidraw diagrams, which are hand-drawn-style visual diagrams. It provides a text guide for diagram elements and a visual tool that renders supplied JSON elements as SVG.

In plain words
What is it for?
Reading the element format and examples, then creating and streaming Excalidraw diagram views with colors, coordinates, and drawing animations.
Why use it?
It gives an assistant the information and rendering path needed to turn structured diagram data into a viewable drawing.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is eaccmk/eaccmk_excalidraw-mcp's own configuration. It tells Claude Code how to work on eaccmk_excalidraw-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything eaccmk_excalidraw-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to eaccmk/eaccmk_excalidraw-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/eaccmk/eaccmk_excalidraw-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/eaccmk/eaccmk_excalidraw-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eaccmk_excalidraw-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for eaccmk_excalidraw-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/eaccmk/eaccmk_excalidraw-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,343 This file is loaded in full into every session.
When invoked 2,343 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02343 $0.02343
Opus 5.5 $0.00937 $0.00937
Sonnet 5.5 $0.00469 $0.00469
Haiku 4.5 $0.00234 $0.00234

Measured 2mo ago against content hash d94205a105f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eaccmk_excalidraw-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Excalidraw MCP App Server

Standalone MCP server that streams Excalidraw diagrams as SVG with hand-drawn animations.

Architecture

server.ts          → 2 tools (read_me, create_view) + resource + cheat sheet
main.ts            → HTTP (Streamable) + stdio transports
src/mcp-app.tsx    → ExcalidrawAppCore (widget logic) + ExcalidrawApp (useApp wrapper)
src/mcp-entry.tsx  → Production entry point: createRoot + ExcalidrawApp
src/global.css     → Animations (stroke draw-on, fade-in) + auto-resize
src/dev.tsx        → Dev entry point: mock app + sample elements + control panel
src/dev-mock.ts    → Mock MCP App with event simulation (sendToolInput, streamElements, etc.)
index-dev.html     → Dev HTML entry (served by vite dev server)
vite.config.dev.ts → Dev-only vite config (resolves from node_modules, no esm.sh externals)

Tools

read_me (text tool, no UI)

Returns a cheat sheet with element format, color palettes, coordinate tips, and examples. The model should call this before create_view.

create_view (UI tool)

Takes elements — a JSON string of standard Excalidraw elements. The widget parses partial JSON during streaming and renders via exportToSvg + morphdom diffing. No Excalidraw React canvas component — pure SVG rendering.

Screenshot as model context: After final render, the SVG is captured as a 512px-max PNG and sent via app.updateModelContext() so the model can see the diagram and iterate on user feedback.

Key Design Decisions

Standard Excalidraw JSON — no extensions

The input is standard Excalidraw element JSON. No label on containers, no start/end on arrows. These are Excalidraw's internal "skeleton" API (convertToExcalidrawElements) — not the standard format.

Why: Standard format means any .excalidraw file's elements array works as input.

Trade-off: Labels require separate text elements with manually computed centered coordinates. The cheat sheet teaches the formula: x = shape.x + (shape.width - text.width) / 2.

Read the full file on GitHub · 206 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 206 lines · 2,343 tokens per session scan A d94205a105f5

Subscribe to this mod's changes

eaccmk_excalidraw-mcp CLAUDE.md is an instructions file published in the GitHub repository eaccmk/eaccmk_excalidraw-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,343 tokens to every session, about $0.0094 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

eaccmk_excalidraw-mcp CLAUDE.md compared with instructions from other repositories

eaccmk_excalidraw-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
eaccmk_excalidraw-mcp CLAUDE.mdeaccmk/eaccmk_excalidraw-mcpInstructions file02mo agoMITA2,343Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode