AI agents use add_card_label to create or update resources in Scrumdo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Scrumdo environment.
Adding a label is a reversible modification of card metadata. It doesn't delete or permanently alter data (Destructive), execute arbitrary operations (Execute), move money (Financial), or merely read data (Read). It fits Write category as it modifies state on the ScrumDo board.
From the tool's definition Tool description states 'Add a single label to a card' - this creates/modifies metadata on a card by adding a new label while preserving existing ones.
Attacks that exploit this kind of access
Add a single label to a card, preserving existing labels. It is categorised as a Write tool in the Scrumdo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Scrumdo MCP server in PolicyLayer and add a rule for add_card_label: 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 Scrumdo. Nothing to install.
add_card_label 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 add_card_label 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 add_card_label. 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.
add_card_label is provided by the Scrumdo MCP server (scrumdollc/scrumdo-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 →