Attach a local file (image, PDF, etc.) to a Trello card.
AI agents use trello_add_attachment to create or update resources in Mtl Trello — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mtl Trello environment.
Attaching files to cards is a data modification that persists but is reversible (attachments can be removed). This is Write-category behavior. Severity is medium because while the operation modifies shared team data and could introduce unwanted files to a collaborative board, attachments are easily removable and do not cause irreversible harm like deletion would.
From the tool's definition Tool description states 'Attach a local file...to a Trello card' — this creates/modifies card data by adding an attachment, a reversible operation.
Attacks that exploit this kind of access
Attach a local file (image, PDF, etc.) to a Trello card. It is categorised as a Write tool in the Mtl Trello MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mtl Trello MCP server in PolicyLayer and add a rule for trello_add_attachment: 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 Mtl Trello. Nothing to install.
trello_add_attachment 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_add_attachment 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_add_attachment. 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_add_attachment is provided by the Mtl Trello MCP server (musictechlab/mtl-trello-mcp). 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 →