Add a link attachment to a card
AI agents use planka_add_link_attachment to create or update resources in Planka MCP Server for Claude — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Planka MCP Server for Claude environment.
This tool creates new data (a link attachment) and modifies an existing card object, making it a Write operation. It is reversible (attachments can be removed), so it does not rise to Destructive. The severity is medium because while it adds metadata, it doesn't alter core project data or enable arbitrary code execution.
From the tool's definition 'Add a link attachment to a card' - this operation creates a new attachment resource associated with a card, modifying the card's state by adding a relationship/reference to an external link.
Attacks that exploit this kind of access
Add a link attachment to a card. It is categorised as a Write tool in the Planka MCP Server for Claude MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Planka MCP Server for Claude MCP server in PolicyLayer and add a rule for planka_add_link_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 Planka MCP Server for Claude. Nothing to install.
planka_add_link_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 planka_add_link_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 planka_add_link_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.
planka_add_link_attachment is provided by the Planka MCP Server for Claude MCP server (nextheberg/planka-mcp-server-for-claude). 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 →