AI agents use trello_create_task to create or update resources in Trello — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trello environment.
Creating a task is a Write operation—it creates data without deleting or overwriting existing content. The severity is medium because a misbehaving agent could spam tasks across boards, degrading project management workflow and requiring manual cleanup, but the impact is limited to non-destructive additions. Confidence is high given the explicit language in both name and description.
From the tool's definition Tool name explicitly states 'create' and description confirms 'Create a new task (card) in a Trello list'. This is a reversible data creation operation.
Attacks that exploit this kind of access
Create a new task (card) in a Trello list with task management features. It is categorised as a Write tool in the Trello MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trello MCP server in PolicyLayer and add a rule for trello_create_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Trello. Nothing to install.
trello_create_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the trello_create_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for trello_create_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
trello_create_task is provided by the Trello MCP server (magnusnilsson/trello-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →