Trello MCP

Live

OAUTH 2.1

BOARDS AND CARDS

Project Management

Every board, card, and checklist your team tracks lives in Trello. Trello MCP gives your agent authenticated access scoped to the user who authorized it.

  • Acts as the user: access and write actions stay tied to the Trello account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: permissions enforced. 90-day audit trail.
Trello MCP
agent · Acme Q3
Run
Which cards in the launch board are still unassigned?
S
trello_list_cards
92ms
Trello agent
6 of 41 cards on Launch Q4 have no member. 4 sit in Ready for dev, 2 in Review.
Sources: 1 board, 5 lists, 41 cards
trellomcp
3 calls
18:29
Message Claude...

Tools your project management agent reaches for on Trello MCP, scoped per user.

CALL ANY TOOL
List boards and cards, move cards between lists, post comments, and manage labels and members through Trello's official MCP server.
trellomcp_trello_read_board
Trello read board
Read Trello boards. Supports listing boards the authenticated user is a member of, listing all boards a user can access within a specific workspace (regardless of membership), fetching a single board by ARI or URL, and listing labels on a board. Actions: - "list": paginated boards the authenticated user is a member of, across all workspaces. Use this for "my boards", "boards I'm on". It does NOT include boards the user could access but has not joined: for those, use "list_by_workspace". By default only open (non-archived) boards are returned; pass filter="all" to include archived boards or filter="closed" for only archived ones. Always include each board's url verbatim in the response. Optionally also filtered by visibility (limit defaults to 25, max 100). The open/closed filter is applied server-side (exact), whereas the visibility filter is applied per page: keep paginating via pageInfo.endCursor while pageInfo.hasNextPage is true to find all matches. - "list_by_workspace": paginated boards the user can access within ONE workspace (requires workspaceId), regardless of whether they are a member. Use this when the user names a workspace: "boards in <workspace>", "what's in this workspace". Supports the same open/closed filter, visibility filter, and pagination as "list". Always include each board's url verbatim in the response. - "get": return a single board by ARI or board URL (e.g. https://trello.com/b/<shortLink>/<slug>), including id, objectId, name, closed, shortLink, lastActivityAt, and url. Always include the board url verbatim as the full literal URL: never replace it with a label such as "View on Trello" or hide it behind link text; never omit it. Embeds the first 25 open lists with a listsHasMore flag; for the full set call trelloReadList with action="list_by_board". - "list_labels": paginated labels on a board (requires boardId; limit defaults to 25, max 100); paginate via nextCursor while hasMore is true.
Parameters
Name
Type
Required
Description
action
string
Required
Action to perform: "list" (my boards), "list_by_workspace" (boards in a workspace), "get" (single board), "list_labels" (labels on a board).
boardId
string
Optional
Trello board identifier. Required for "get" and "list_labels"; not allowed for other actions. For action="get", accepts an ARI (e.g. ari:cloud:trello::board/workspace/<workspaceId>/<boardId>) or a Trello board URL (e.g. https://trello.com/b/<shortLink>/<slug>). For all other actions, boardId must be a board ARI: board URLs/short links are not supported.
cursor
string
Optional
Pagination cursor. Only valid for paginated actions ("list", "list_by_workspace", "list_labels").
filter
string
Optional
Filter boards by open/closed state. "open" (default) returns only active (non-archived) boards; "closed" returns only archived boards; "all" returns both. Only valid when action="list" or action="list_by_workspace".
limit
integer
Optional
Maximum results per page. Defaults to 25, max 100. Only valid for paginated actions ("list", "list_by_workspace", "list_labels").
visibility
string
Optional
Filter boards by visibility. Only valid when action="list" or action="list_by_workspace".
workspaceId
string
Optional
Trello workspace identifier. Required for action="list_by_workspace"; not allowed for other actions. Accepts an ARI (e.g. ari:cloud:trello::workspace/<workspaceId>).
trellomcp_trello_read_card
Trello read card
trellomcp_trello_read_checklist
Trello read checklist
trellomcp_trello_read_inbox
Trello read inbox
trellomcp_trello_read_list
List trello read
trellomcp_trello_read_member
Trello read member
trellomcp_trello_read_planner
Trello read planner
trellomcp_trello_read_workspace
Trello read workspace
trellomcp_trello_search
Search trello
trellomcp_trello_write_board
Trello write board
trellomcp_trello_write_card
Trello write card
trellomcp_trello_write_checklist
Trello write checklist
trellomcp_trello_write_inbox
Trello write inbox
trellomcp_trello_write_list
List trello write
trellomcp_trello_write_planner
Trello write planner
Build your Agent
Drop the toolkit in, point it at the user, and your project management agent can use Trello from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Trello MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["trellomcp"], toolNames: [
"trellomcp_trello_read_board",
"trellomcp_trello_read_card",
"trellomcp_trello_read_checklist"
] },
pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Which cards in the launch board are still unassigned?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Trello MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["trellomcp"], toolNames: [
"trellomcp_trello_read_board",
"trellomcp_trello_read_card",
"trellomcp_trello_read_checklist"
] },
pageSize: 100,
});

const openai = new OpenAI();
const res = await openai.responses.create({
model: "gpt-5",
tools: tools.map((t) => t.openai),
input: "Which cards in the launch board are still unassigned?",
});
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Trello MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["trellomcp"], toolNames: [
"trellomcp_trello_read_board",
"trellomcp_trello_read_card",
"trellomcp_trello_read_checklist"
] },
pageSize: 100,
});

const anthropic = new Anthropic();
const msg = await anthropic.messages.create({
model: "claude-opus-4-6",
max_tokens: 1024,
tools: tools.map((t) => t.anthropic),
messages: [{ role: "user", content: "Which cards in the launch board are still unassigned?" }],
});
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Trello MCP tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["trellomcp"], toolNames: [
"trellomcp_trello_read_board",
"trellomcp_trello_read_card",
"trellomcp_trello_read_checklist"
] },
pageSize: 100,
});

const agent = new Agent({
name: "trellomcp_agent",
model: "gemini-2.5-pro",
instruction: "Act as the project management agent for the signed-in user.",
tools,
});
await agent.run("Which cards in the launch board are still unassigned?");
Try these prompts
Paste any prompt into your agent to start using Trello.
Board hygiene
Copy the prompt
Copied
Which cards on the launch board have no assignee?
Copy the prompt
Copied
List cards with a due date in the past.
Copy the prompt
Copied
Show every card sitting in Review for more than a week.
Planning
Copy the prompt
Copied
Create a card for the auth migration in the Ready for dev list.
Copy the prompt
Copied
Move the billing bug card to In progress and assign it to me.
Copy the prompt
Copied
Add a checklist to the release card with the four deploy steps.
Reporting
Copy the prompt
Copied
Summarize what moved to Done on the launch board this week.
Copy the prompt
Copied
Count open cards per list on the roadmap board.
Copy the prompt
Copied
Which labels are used most across my boards?
SEE HOW AUTH WORKS
Users authorize Trello once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Trello MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Trello MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Trello MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Trello MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.
Engineering Teams
Engineering standup agent
Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.
Engineering Teams
DevOps assistant agent
Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
People Ops and HR teams
Performance review collector
Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.
Test other agents
Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
Engineering standup agent
Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.
ENGINEERING
DevOps assistant agent
Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
PEOPLE OPS
Performance review collector agent
Collect review feedback from Airtable and Google Forms per manager, summarise each report in Notion, and DM the digest in Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Trello today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Trello as the user or as a shared key?
As the user. Each member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Trello oauth 2.1 credential stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Trello?
Yes. Pass a tool name filter to listScopedTools so the project management agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Trello.
What happens when a user revokes Trello access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent reach boards the user was never added to?
No. Trello MCP resolves the authorizing user's membership, so only boards that user belongs to are visible. Private boards in other workspaces stay inaccessible, and board-level permissions apply on every agent call.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""trellomcp"": {
""url"": ""https://mcp.scalekit.com/trellomcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.trellomcp]
url = ""https://mcp.scalekit.com/trellomcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""trellomcp"": {
""url"": ""https://mcp.scalekit.com/trellomcp"",
""type"": ""http""
}
}
}