AI agents use set_card_spec 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.
The tool appears to modify card specifications on a ScrumDo project management board. This is a reversible write operation (specifications can be updated again), not destructive or execute-class. Sibling tools show patterns of board manipulation without deletion. Medium severity reflects typical blast radius of incorrect specification changes on team task tracking—disruptive but recoverable.
From the tool's definition Tool name 'set_card_spec' indicates setting/modifying card specifications on a ScrumDo board. The prefix 'set_' and context of sibling tools (add_comment, add_card_label, assign_card, archive_card) confirm this is a write operation.
Attacks that exploit this kind of access
set_card_spec. 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 set_card_spec: 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.
set_card_spec 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 set_card_spec 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 set_card_spec. 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.
set_card_spec 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 →