things-mcp: Instructions file for Claude Code

CLAUDE.md

things-mcp CLAUDE.md is an instructions file for Claude Code from hald/things-mcp. It costs 1,043 tokens per session, scanned A, original, MIT.

Repository instructions for Things MCP, a server that connects Claude Desktop to the Things 3 task-management app on macOS. They cover setup, commands, transports, and tests.

In plain words
What is it for?
Use them when installing dependencies, starting the server over standard input or HTTP, or testing task, project, area, and tag data handling.
Why use it?
They explain how to run and verify the bridge without guessing its package manager or connection mode.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

Nothing to install: this file belongs to hald/things-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/hald/things-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hald/things-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 things-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/hald/things-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hald/things-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,043 This file is loaded in full into every session.
When invoked 1,043 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 $0.01043 $0.01043
Opus 5.5 $0.00417 $0.00417
Sonnet 5.5 $0.00209 $0.00209
Haiku 4.5 $0.00104 $0.00104

Measured 11d ago against content hash 866c7d202e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

things-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 11d 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

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

Commands

Development Setup

# Install dependencies (uses uv package manager)
uv sync

# Run the MCP server (stdio transport, default)
uv run things-mcp

# Run with HTTP transport
THINGS_MCP_TRANSPORT=http uv run things-mcp

Testing

The project includes a comprehensive unit test suite covering URL scheme construction and data formatting functions.

# Install test dependencies
uv sync --extra test

# Run all tests
uv run pytest

# Run tests with verbose output
uv run pytest -v

# Run specific test file
uv run pytest tests/test_url_scheme.py

# Run tests matching a pattern
uv run pytest -k "test_format"

Test coverage includes:

  • All URL construction functions (add, update, show, search)
  • Authentication token handling
  • Data formatting for todos, projects, areas, and tags
  • Error handling and edge cases
  • Mock external dependencies (Things.py, shell commands)

Architecture Overview

This is a Model Context Protocol (MCP) server that bridges Claude Desktop with the Things 3 task management app on macOS. The architecture consists of:

  1. src/things_mcp/server.py - Main MCP server implementation using FastMCP (3.x)
    • Defines all MCP tools for interacting with Things (26 tools)
    • List views (inbox, today, upcoming, etc.)
    • CRUD operations for todos/projects/areas (Areas have create/read/update — no delete by design; see below)
    • Search and tag operations
    • Things URL scheme integration
    • Implements Someday project filtering to match Things UI behavior
    • Pagination + structured responses: the 16 list/search read tools accept optional limit/offset and return a FastMCP ToolResult carrying both a human-readable text channel and a structured_content envelope {items, count, total, offset, limit}. Two helpers drive this: _paginate_format (text) and _paginate_result (wraps text + JSON-safe structured data); _error_result wraps early-return/validation errors. get_tag_usage intentionally stays a plain string.

Read the full file on GitHub · 95 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. 11d ago Changed 866c7d202e46
  2. 2mo ago First seen · 95 lines · 1,043 tokens per session scan A 4cc10ab30ea3

Subscribe to this mod's changes

things-mcp CLAUDE.md is an instructions file published in the GitHub repository hald/things-mcp (637 stars, last pushed 12d ago), licensed MIT. It adds 1,043 tokens to every session, about $0.0042 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

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

things-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
things-mcp CLAUDE.mdhald/things-mcpInstructions file63712d agoMITA1,043Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, 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