Claude TrelloSAFE
A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/hrs-asano-claude-mcp-trello)
A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards. This server enables seamless integration with Trello's API while handling rate limiting, type safety, and error handling automatically.
Features
- Full Trello Board Integration: Interact with cards, lists, and board activities
- Built-in Rate Limiting: Respects Trello's API limits (300 requests/10s per API key, 100 requests/10s per token)
- Type-Safe Implementation: Written in TypeScript with comprehensive type definitions
- Input Validation: Robust validation for all API inputs
- Error Handling: Graceful error handling with informative messages
Available Tools
trello_get_cards_by_list
Retrieves a list of cards contained in the specified list ID.
{
name: "trello_get_cards_by_list",
arguments: {
listId: string; // Trello list ID
}
}trello_get_lists
Retrieves all lists in the specified board.
{
name: "trello_get_lists",
arguments: {
boardId: string; // The ID of the Trello board to get lists from
}
}trello_get_recent_activity
Retrieves the most recent activity for a specified board. The limit argument can specify how many to retrieve (default: 10).
{
name: "trello_get_recent_activity",
arguments: {
boardId: string; // The ID of the Trello board to get activity from
limit?: number; // Optional: number of activities to retrieve
}
}trello_add_card
Adds a card to the specified list.
{
name: "trello_add_card",
arguments: {
listId: string; // The ID of263c11fdd5c2OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add server-trello --env TRELLO_API_KEY=${TRELLO_API_KEY} --env TRELLO_TOKEN=${TRELLO_TOKEN} -- npx -y @modelcontextprotocol/[email protected]{
"mcpServers": {
"server-trello": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/[email protected]"
],
"env": {
"TRELLO_API_KEY": "${TRELLO_API_KEY}",
"TRELLO_TOKEN": "${TRELLO_TOKEN}"
}
}
}
}Exposed tools (12)
9 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
trello_add_card | write | Adds a card to the specified list. |
trello_add_list | write | Adds a new list to the specified board. |
trello_archive_card | read | Archives (closes) the specified card. |
trello_archive_list | read | Archives (closes) the specified list. |
trello_download_attachment | read | Downloads a specific attachment from a Trello card. For files uploaded directly to Trello, returns the content as base64-encoded data. For external links, returns the URL. Use trello_get_card_attachments first to get the attachment ID. |
trello_get_card_attachments | read | Retrieves all attachments from a specified card. Returns attachment metadata including name, file size, MIME type, and URL. Use this to discover what attachments exist on a card before downloading. |
trello_get_cards_by_list | read | Retrieves a list of cards contained in the specified list ID. |
trello_get_lists | read | Retrieves all lists in the specified board. |
trello_get_my_cards | read | Retrieves all cards related to your account. |
trello_get_recent_activity | read | Retrieves the most recent activity for a specified board. The |
trello_search_all_boards | read | Performs a cross-board search across all boards in the workspace (organization) (depending on plan/permissions). |
trello_update_card | write | Updates the content of a card. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, axios, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, eslint, eslint-config-prettier, eslint-plugin-prettier
Gates applied: no_behavioural_pass.
263c11fdd5c2full audit observations/trust-audit/mcp-server/hrs-asano__claude-trello.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 263c11fdd5c2 | SAFE | B | 89 | first audit |
Questions
What is the Claude Trello MCP server?
A Model Context Protocol (MCP) server that provides tools for interacting with Trello boards.
What tools does Claude Trello expose?
12 in total: 9 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Claude Trello safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Claude Trello need?
It reads TRELLO_API_KEY and TRELLO_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Claude Trello run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @modelcontextprotocol/server-trello at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (263c11fdd5c2), read on 2026-10-08. The repository is watched and re-audited when it changes.