drafts-mcp-server: Instructions file for Claude Code

CLAUDE.md

drafts-mcp-server CLAUDE.md is an instructions file for Claude Code from agiletortoise/drafts-mcp-server. It costs 445 tokens per session, scanned A, original, MIT.

Repository instructions for a server that lets AI assistants control the macOS Drafts app through AppleScript. AppleScript is Apple's scripting language for automating Mac applications, and MCP is a standard connection method for AI tools.

In plain words
What is it for?
Use them when installing dependencies, building or watching the TypeScript project, running the server, testing it with MCP Inspector, or adding Drafts operations.
Why use it?
They give developers the commands, file locations, architecture, and conventions needed to build, run, inspect, and extend the server.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/agiletortoise/drafts-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/agiletortoise/drafts-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 445 This file is loaded in full into every session.
When invoked 445 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 $0.00445 $0.00445
Opus 5.5 $0.00178 $0.00178
Sonnet 5.5 $0.00089 $0.00089
Haiku 4.5 $0.00044 $0.00044

Measured 2mo ago against content hash 64110364a036, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drafts-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 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 · 46 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and Development Commands

npm install          # Install dependencies
npm run build        # Build TypeScript to dist/
npm run watch        # Build in watch mode for development
npm run inspector    # Test server with MCP Inspector web interface
node dist/index.js   # Run the server directly

Architecture

This is an MCP (Model Context Protocol) server that enables AI assistants to interact with the macOS Drafts app via AppleScript. It uses stdio transport for communication.

Source Files

  • src/index.ts: MCP server entry point. Defines the TOOLS array with all tool schemas, the DraftsMCPServer class, and request handlers that route tool calls to drafts.ts functions.

  • src/drafts.ts: High-level Drafts operations. Each function builds an AppleScript, executes it via executeAppleScript(), and parses the result. Contains interfaces: Workspace, Draft, Action.

  • src/applescript.ts: Low-level AppleScript execution utilities. executeAppleScript() runs scripts via osascript, escapeAppleScriptString() sanitizes user input for safe AppleScript embedding.

Adding a New Tool

  1. Add the function to src/drafts.ts with AppleScript logic
  2. Add tool schema to TOOLS array in src/index.ts
  3. Add case handler in the switch statement in setupHandlers()

Key Patterns

  • All user input must be escaped with escapeAppleScriptString() before embedding in AppleScript
  • AppleScript errors are caught with try/on error blocks and return "ERROR: " or "NOT_FOUND" sentinel values
  • Tool handlers return { content: [{ type: 'text', text: '...' }], isError?: boolean }
  • Draft identifiers use UUIDs from Drafts app

Requirements

  • macOS only (AppleScript)
  • Node.js 18+
  • Drafts app installed
  • First run requires granting Automation permissions in System Preferences
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 · 46 lines · 445 tokens per session scan A 64110364a036

Subscribe to this mod's changes

drafts-mcp-server CLAUDE.md is an instructions file published in the GitHub repository agiletortoise/drafts-mcp-server (47 stars, last pushed 5mo ago), licensed MIT. It adds 445 tokens to every session, about $0.0018 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 2026-08-30.

Related

drafts-mcp-server CLAUDE.md compared with instructions from other repositories

drafts-mcp-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
drafts-mcp-server CLAUDE.mdagiletortoise/drafts-mcp-serverInstructions file475mo agoMITA445Claude 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