What makes Trello notable?

1.3K downloads. Trust evidence available

How should Trello be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Trello

Work safely in one connected Trello workspace Skill: Trello Owner: maverick Summary: Work safely in one connected Trello workspace Tags: latest:1.1.0 Version history: v1.1.0 | 2026-08-03T20:41:53.150Z | user Migrate Trello to official hosted MCP v1.0.4 | 2026-05-21T10:05:35.322Z | user Convert skill metadata frontmatter to YAML v1.0.3 | 2026-05-17T17:00:20.119Z | user Update mcporter setup and invocation contracts v1.0.2 | 2026-05-14T11:59:12.329Z | user Refresh

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.1.0release · observed Aug 3, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17b4scyfsybdcep8c0034pgs186087n:maverick-trello-mcp

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-maverick-maverick-trello-mcp/snapshot"

Documentation

CLAWHUB

32,076 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: maverick-trello-mcp
description: Search, read, and safely update one selected Trello workspace through Trello's official hosted MCP server. Use for boards, members, cards, lists, checklists, and workspace search.
metadata:
openclaw:
emoji: '🗂️'
homepage: https://support.atlassian.com/trello/docs/connect-trello-to-ai-assistants-with-trello-mcp/
primaryEnv: MAVERICK_TRELLO_MCP_REFRESH_TOKEN
requires:
bins:
- mcporter
env:
- MAVERICK_TRELLO_MCP_REFRESH_TOKEN
- MAVERICK_TRELLO_MCP_CLIENT_ID
- MAVERICK_TRELLO_MCP_ACCESS_TOKEN
setup:
script: scripts/setup.sh
install:
- id: node
kind: node
package: [email protected]
bins:
- mcporter
label: Install mcporter (node)
---

# Trello

## How to use this skill

This skill connects directly to Trello's official hosted MCP server at `https://mcp.trello.com/v1`. The OAuth connection selects exactly one Trello workspace. Never claim access to another workspace without a separate connection.

Discover the live schema before calling a tool:

```sh
mcporter --config {baseDir}/mcporter.json list maverick-trello-mcp --schema
```

Call only a tool in the configured allowlist:

```sh
mcporter --config {baseDir}/mcporter.json call --output json maverick-trello-mcp.<tool> key=value
```

The allowed tool names are `trelloReadMember`, `trelloReadBoard`, `trelloReadCard`, `trelloWriteList`, `trelloWriteCard`, `trelloWriteChecklist`, and `trelloSearch`. If the live server advertises additional tools, they remain unavailable until Maverick's reviewed allowlist changes.

## Safety and approvals

- Read and search operations may run without approval when they match the user's request.
- Every `trelloWriteList`, `trelloWriteCard`, and `trelloWriteChecklist` call requires explicit approval before invocation, including create, update, move, comment, assign, checklist-edit, and archive actions.
- Inspect the current board/list/card state before a write and describe the intended change in the approval request.
- Prefer archive operations when removal is requested. Never attempt a permanent destructive delete, even if a future server advertises one.
- mcporter mechanically rejects tools outside the exact allowlist. For an allowed aggregate write tool, treat the live schema as the action contract and do not invoke a new or unreviewed action until Maverick's policy is updated.

## Authentication

Maverick performs MCP-native OAuth Authorization Code with PKCE and dynamic public-client registration, then seeds the access token, refresh token, and issued client id into mcporter's vault through `scripts/setup.sh`. mcporter uses OAuth protected-resource discovery when refreshing, which preserves Trello's `https://mcp.trello.com/v1` resource indicator.

Setup requires these credential variables:

- `MAVERICK_TRELLO_MCP_REFRESH_TOKEN`
- `MAVERICK_TRELLO_MCP_CLIENT_ID`
- `MAVERICK_TRELLO_MCP_ACCESS_TOKEN`

Optional

_meta.json

{
  "ownerId": "kn734qkn0pkds34pv28ksc0p7h81ha6e",
  "slug": "maverick-trello-mcp",
  "version": "1.1.0",
  "publishedAt": 1785789713150
}

skill-card.md

## Description:

Search, read, and safely update one selected Trello workspace through Trello's official hosted MCP server. Use for boards, members, cards, lists, checklists, and workspace search.

This skill is ready for commercial/non-commercial use.

## Publisher:

[maverick](https://clawhub.ai/user/maverick)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and teams use this skill to let an agent search, read, and update boards, cards, lists, checklists, and members in one OAuth-connected Trello workspace, with approval required before writes or archive actions.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: OAuth credentials or the mcporter vault could grant access to the selected Trello workspace if exposed.

Mitigation: Keep the environment variables and mcporter vault private, and rotate or revoke Trello credentials if exposure is suspected.

Risk: Approved write or archive actions can modify content in the connected Trello workspace.

Mitigation: Inspect the current board, list, or card state first and require explicit approval for every write or archive action.

Risk: Replaying stale setup input can overwrite a newer refresh token in the local vault.

Mitigation: Run setup only after a fresh connection or credential rotation using the freshest credential state.

## Reference(s):

- [Trello MCP guide](https://support.atlassian.com/trello/docs/connect-trello-to-ai-assistants-with-trello-mcp/)
- [Trello MCP endpoint](https://mcp.trello.com/v1)
- [mcporter 0.12.3](https://github.com/openclaw/mcporter/tree/v0.12.3)
- [ClawHub skill page](https://clawhub.ai/maverick/skills/maverick-trello-mcp)

## Skill Output:

**Output Type(s):** [guidance, shell commands, configuration, API calls]

**Output Format:** [Markdown guidance with shell command examples and JSON MCP configuration]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Uses OAuth credentials and an allowlisted Trello MCP tool set.]

## Skill Version(s):

1.1.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

mcporter.json

{
  "imports": [],
  "mcpServers": {
    "maverick-trello-mcp": {
      "baseUrl": "https://mcp.trello.com/v1",
      "transport": "http",
      "auth": "oauth",
      "oauthClientIdEnv": "MAVERICK_TRELLO_MCP_CLIENT_ID",
      "oauthTokenEndpointAuthMethod": "none",
      "allowedTools": [
        "trelloReadMember",
        "trelloReadBoard",
        "trelloReadCard",
        "trelloWriteList",
        "trelloWriteCard",
        "trelloWriteChecklist",
        "trelloSearch"
      ]
    }
  }
}

agents/openai.yaml

interface:
  display_name: 'Trello'
  short_description: 'Work safely in one connected Trello workspace'
  default_prompt: 'Use only the allowlisted official Trello MCP tools. Read first, require approval for every write or archive action, and never attempt permanent deletion.'

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.