trello-mcp

trello-mcp

A Trello MCP server that enables searching cards by custom field values and managing board data with compact responses.

Category
访问服务器

README

trello-mcp

A small MCP server for Trello, built around the one thing the popular Trello MCP servers don't do: searching cards by custom field (e.g. find every card where the AI Ready field equals Claude kiosk).

It talks to the Trello REST API directly using your API key + token, returns compact results (no multi-hundred-KB board dumps), and resolves boards/cards by id, 8-char shortLink, URL, or name.

Tools

Tool What it does
list_boards All boards you can access — {id, name, shortLink, url}, nothing else.
list_custom_fields Custom fields on a board + the allowed options for list-type fields. Use it to discover field names/values.
find_cards Main tool. Find cards on a board, filtered by a custom field (fieldName + value, or values to match ANY of several), and/or listName, and/or label. Matching is case-insensitive (exact first, then substring). Omit value(s) to match "field is set".
get_card Full content of one card: description, custom field values, checklists, attachments, comments, members, due date.
add_comment Post a comment to a card (ask a clarifying question, or log progress).
set_custom_field Set/clear a custom field on a card; createOption:true adds a new list option. Used to mark status (e.g. AI Ready → Done).
attach_file Attach a file to a card — a local file by path or a remote file by url. Handy for posting a result file when finishing a task.

Setup

1. Get Trello credentials

Create a Power-Up at https://trello.com/power-ups/admin, grab the API Key from its API Key tab, then generate a Token:

https://trello.com/1/authorize?expiration=never&scope=read,write&response_type=token&name=trello-mcp&key=YOUR_API_KEY

The Power-Up Secret is for OAuth and is NOT used here — only API Key + Token.

2. Register with Claude Code — zero clone, straight from GitHub

claude mcp add trello-cf --scope user \
  -e TRELLO_API_KEY=YOUR_KEY \
  -e TRELLO_TOKEN=YOUR_TOKEN \
  -- npx -y github:AxGrid/trello-mcp

--scope user makes it available in every project. npx installs and runs it on first launch — no git clone, no npm install. Restart Claude Code afterwards.

Or in claude_desktop_config.json / any MCP client:

{
  "mcpServers": {
    "trello-cf": {
      "command": "npx",
      "args": ["-y", "github:AxGrid/trello-mcp"],
      "env": { "TRELLO_API_KEY": "YOUR_KEY", "TRELLO_TOKEN": "YOUR_TOKEN" }
    }
  }
}

npx caches the GitHub package per resolved commit. To force a pull of the latest main, clear it once: npx clear-npx-cache (or rm -rf ~/.npm/_npx).

Local / dev install

git clone git@github.com:AxGrid/trello-mcp.git && cd trello-mcp && npm install
# then point the client at: node /abs/path/to/trello-mcp/server.mjs

Example

Find cards on the Stellar Kiosk board where AI Ready = Claude kiosk and let's solve them.

Claude calls find_cards({ board: "Stellar Kiosk", fieldName: "AI Ready", value: "Claude kiosk" }), then get_card(...) on the match.

Task lifecycle via a custom field

A single list-type field (here AI Ready) doubles as a status. Suggested values:

State Value How
Queued for AI Claude kiosk, Claude Module, … pick up with find_cards({fieldName:"AI Ready", values:["Claude kiosk","Claude Module"]})
Needs a human answer Need response set_custom_field(card, "AI Ready", "Need response", createOption:true) + add_comment(card, "question…")
Done Done optionally attach_file(card, path:"…/result.…"), then set_custom_field(card, "AI Ready", "Done", createOption:true)

Setting a new state moves the card out of the "queued" search automatically, since the field no longer equals a queued value. createOption:true is only needed the first time a value is introduced.

Self-test

Runs the core logic against your real account (read-only):

TRELLO_API_KEY=... TRELLO_TOKEN=... TEST_BOARD="Your Board" node selftest.mjs

Requirements

Node 18+ (uses the built-in global fetch). The only runtime dependency is @modelcontextprotocol/sdk.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选