What is things-cloud-mcp CLAUDE.md?

Project instructions for a Go server that connects the Things cloud task service to AI agents through MCP. The server supports multiple users, login tokens, a web page, and SQLite-based local data.

Use them when building, testing, running, or changing the things-cloud-mcp server, including its authentication, user handling, task synchronization, or storage.

They explain the repository's build, test, configuration, and data-flow rules so an agent can modify it safely.

How wbopan/things-cloud-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to wbopan/things-cloud-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/wbopan/things-cloud-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/wbopan/things-cloud-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wbopan/things-cloud-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/wbopan/things-cloud-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/wbopan/things-cloud-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wbopan/things-cloud-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wbopan/things-cloud-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wbopan/things-cloud-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,517 This file is loaded in full into every session.

When invoked 1,517 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01517	$0.01517
Opus 5.5	$0.00607	$0.00607
Sonnet 5.5	$0.00303	$0.00303
Haiku 4.5	$0.00152	$0.00152

Measured 2mo ago against content hash 26f141287046, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

things-cloud-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Do NOT use the Things Cloud MCP tools directly** (e.g. `things_find_tasks`, `things_edit_item`) for testing during development. Those call the deployed production instance, which does not reflect local code changes. Al

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 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.

Build & Run

/usr/local/go/bin/go build -o things-cloud-mcp .    # build
./things-cloud-mcp                                   # run (default port 8080)

No linter configured. Run tests with /usr/local/go/bin/go test ./.... Verify build with go build ./....

Environment variables: PORT (default 8080), JWT_SECRET (base64, auto-generated if unset), DATA_DIR (default data/, for SQLite), THINGS_DEBUG (enables SDK debug logging).

Architecture

Single-package Go MCP server (~3 files): main.go (tools + state), oauth.go (OAuth 2.1 + JWT), landing.go (web UI).

Multi-user data flow:

HTTP request arrives with Authorization: Basic (email:password) or Bearer (JWT from OAuth flow)
UserManager.httpContextFunc() stores credentials in context
wrap() extracts user → UserManager.GetOrCreateUser() → per-user ThingsMCP instance (cached by email)
Each ThingsMCP holds its own thingscloud.Client, thingscloud.History (sync cursor), and memory.State (in-memory task graph)
Read handlers call syncAndRebuild() then query state.Tasks; write handlers call writeAndSync()

Key SDK types (from github.com/arthursoares/things-cloud-sdk):

Task.CreationDate is time.Time (non-nullable); ScheduledDate, DeadlineDate, CompletionDate are *time.Time
TaskType: 0=task, 1=project, 2=heading. TaskStatus: 0=pending, 2=canceled, 3=completed
TaskSchedule: 0=inbox, 1=anytime, 2=someday. Task.StartBucket: 0=default, 1=tonight (wire: sb)

MCP Tool Design

Before adding or modifying MCP tool definitions, check the MCP builder skill for current guidelines on tool naming, parameter descriptions, enum design, output structure, and behavioral annotations.

Coding Patterns

Tool handlers follow: func (t *ThingsMCP) handle<Name>(ctx, req) (*CallToolResult, error). Tool definitions use mcp.NewTool() with mcp.WithString/WithBoolean params. All registered via wrap() which handles user extraction. Exception: things_diagnose uses a custom handler with extractCredentials() because it needs raw email/password to create a fresh diagnostic client.

Read the full file on GitHub · 79 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.

2mo ago First seen · 79 lines · 1,517 tokens per session scan A 26f141287046

Subscribe to this mod's changes

things-cloud-mcp CLAUDE.md is an instructions file published in the GitHub repository wbopan/things-cloud-mcp (43 stars, last pushed 1mo ago), licensed MIT. It adds 1,517 tokens to every session, about $0.0061 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Go mcp things3

things-cloud-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
things-cloud-mcp CLAUDE.mdwbopan/things-cloud-mcp	Instructions file	43	1mo ago	MIT	A	1,517	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

things-cloud-mcp: Instructions file for Claude Code