What is mcp-trello CLAUDE.md?

Development instructions for an MCP Trello server, covering local development, building, deployment, code formatting, linting, testing, and debugging. Trello is a task-management service built around boards and cards.

Use them when developing or maintaining the server, including starting watch mode, building HTTP or standard-input versions, running checks, formatting code, and debugging.

They give an agent the project's standard commands and help it make changes that fit the repository's development and release process.

How Hint-Services/mcp-trello configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Hint-Services/mcp-trello. 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/Hint-Services/mcp-trello/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Hint-Services/mcp-trello

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/hint-services/mcp-trello/claude-md/github.svg)](https://agentmods.dev/instructions/hint-services/mcp-trello/claude-md)

Your own site

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

Per session 819 This file is loaded in full into every session.

When invoked 819 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.

Model	Per session	Once invoked
Fable 5.1	$0.00819	$0.00819
Opus 5.5	$0.00328	$0.00328
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash e26c3e35d598, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-trello 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 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.

Common Commands

Development

npm run dev - Start development server with HTTP streaming interface and hot reloading
npm run dev:stdio - Start development with TypeScript watch mode and MCP inspector (legacy)
npm run watch - TypeScript watch mode only
npm run inspector - Run MCP inspector for debugging tools

Build Commands

npm run build - Build HTTP streaming version (default)
npm run build:http - Build HTTP streaming version using Smithery
npm run build:stdio - Build stdio version for backwards compatibility

Deployment

npm start - Start HTTP streaming server (default)
npm run start:http - Start HTTP streaming server
npm run start:stdio - Start stdio server (backwards compatibility)

Quality Assurance

npm run lint - Lint code with Biome
npm run lint:fix - Lint and auto-fix issues
npm run format - Check code formatting with Biome
npm run format:fix - Format code with Biome

Testing/Debugging

npm run debug - Start server with Node.js inspector
npm run debug:watch - Debug mode with TypeScript watch
npm run logs - Tail Claude MCP logs

Architecture

This is a Model Context Protocol (MCP) server that provides Trello integration tools for AI assistants. It supports both HTTP streaming and stdio interfaces. The architecture follows a clean separation of concerns:

Core Components

Main Server (src/index.ts)

Exports factory function for HTTP streaming interface
Maintains backwards compatibility with stdio transport
Environment variable validation for Trello credentials
Configuration schema using Zod for type safety
Graceful shutdown handling for both interfaces

Trello Client (src/trello/client.ts)

Axios-based HTTP client with built-in rate limiting
Tool registration method that defines all available Trello operations
Error handling with retry logic for rate limits
Type-safe API interactions using Zod schemas

Read the full file on GitHub · 86 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 · 86 lines · 819 tokens per session scan A e26c3e35d598

Subscribe to this mod's changes

mcp-trello CLAUDE.md is an instructions file published in the GitHub repository Hint-Services/mcp-trello (10 stars, last pushed 12mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0033 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.

Project management

mcp-trello CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-trello CLAUDE.mdHint-Services/mcp-trello	Instructions file	10	12mo ago	MIT	A	819	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

mcp-trello: Instructions file for Claude Code