tldraw-mcp-server: Instructions file for Claude Code

CLAUDE.md

tldraw-mcp-server CLAUDE.md is an instructions file for Claude Code from AndresMuelas2004/tldraw-mcp-server. It costs 455 tokens per session, scanned A, original, MIT.

A developer guide for tldraw-mcp-server, a server that lets software work with documents made in tldraw, a visual drawing and diagramming tool. It documents how the TypeScript project is built, organised, and extended.

In plain words
What is it for?
Use it when building or running the server, registering MCP tools, modifying document or shape operations, working with schemas, or changing utilities and state handling.
Why use it?
It gives maintainers a shared reference for the server’s build commands, in-memory document state, tools, schemas, and naming patterns. This makes changes easier to place correctly in the codebase.

Instructions file for Claude Code

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

This is AndresMuelas2004/tldraw-mcp-server's own configuration. It tells Claude Code how to work on tldraw-mcp-server 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 tldraw-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AndresMuelas2004/tldraw-mcp-server. 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/AndresMuelas2004/tldraw-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AndresMuelas2004/tldraw-mcp-server

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 tldraw-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/andresmuelas2004/tldraw-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/andresmuelas2004/tldraw-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/andresmuelas2004/tldraw-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/andresmuelas2004/tldraw-mcp-server/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 tldraw-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/andresmuelas2004/tldraw-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/andresmuelas2004/tldraw-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 455 This file is loaded in full into every session.
When invoked 455 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 $0.00455 $0.00455
Opus 5 $0.00228 $0.00228
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured 10d ago against content hash 7828056c7dde, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tldraw-mcp-server 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 10d 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 · 31 lines

What it actually says

tldraw MCP Server — Developer Guide

Build & Run

npm run build    # Compiles TypeScript → dist/
npm start        # Runs the MCP server (stdio transport)

Architecture

  • Entry: src/index.ts — creates the MCP server, connects stdio transport
  • Tool registration: src/register-tools.ts — registers all 30+ tools with the MCP SDK
  • State: src/state/document-state.ts — singleton DocumentState that holds the in-memory tldraw document (records, pages, shapes, bindings)
  • Tools: src/tools/ — one file per category (document, shapes-*, connections, manipulation, grouping, ordering, pages, query, camera, assets)
  • Schemas: src/schemas/ — Zod schemas for shape props and shared styles
  • Utils: src/utils/ — ID generation, fractional indices, rich text conversion, default props, response helpers

Key Patterns

  • Tool registration: Each tool file exports a function that takes the MCP Server instance and calls server.tool(name, schema, handler).
  • State management: All tools operate on the shared state singleton (imported from document-state.ts). The state holds a flat map of tldraw records.
  • Shape creation: Tools use createShapeId() for IDs, getIndexAbove() for z-ordering indices, and getDefault*Props() for base shape properties.
  • Rich text: tldraw uses a custom rich text format. Use textToRichText(plainString) to convert plain text.
  • Arrow bindings: Created as separate binding records that link an arrow's terminal (start/end) to a target shape.

File Naming Conventions

  • shapes-*.ts — one file per shape type (geo, text, arrow, note, frame, draw, line, image, video, bookmark, embed, highlight)
  • Tool names use tldraw_ prefix with snake_case (e.g., tldraw_create_geo)
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. 10d ago First seen · 31 lines · 455 tokens per session scan A 7828056c7dde

Subscribe to this mod's changes

tldraw-mcp-server CLAUDE.md is an instructions file published in the GitHub repository AndresMuelas2004/tldraw-mcp-server (2 stars, last pushed 5mo ago), licensed MIT. It adds 455 tokens to every session, about $0.0023 per session on Opus 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

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens