Create a new card in a specific list.
AI agents use create_card to create or update resources in Mcp Trello — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Trello environment.
This tool creates a new card in a Trello list. Card creation is a reversible operation—cards can be deleted, moved, or modified afterward. It does not execute arbitrary code, trigger destructive actions, or commit financial transactions. It fits the Write category: creates data reversibly. Severity is low because the blast radius of an AI agent accidentally creating unwanted cards is minimal and easily correctable.
From the tool's definition Tool name 'create_card' and description 'Create a new card in a specific list' indicate data creation that is reversible (cards can be deleted or moved).
Attacks that exploit this kind of access
Create a new card in a specific list. It is categorised as a Write tool in the Mcp Trello MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Trello MCP server in PolicyLayer and add a rule for create_card: 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 Mcp Trello. Nothing to install.
create_card 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 create_card 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 create_card. 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.
create_card is provided by the Mcp Trello MCP server (mbeauv/mcp-trello). 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 →