trello-mcp
A Trello MCP server that enables searching cards by custom field values and managing board data with compact responses.
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" }
}
}
}
npxcaches the GitHub package per resolved commit. To force a pull of the latestmain, clear it once:npx clear-npx-cache(orrm -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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.