AI agents call get_spec_complexity to retrieve information from Scrumdo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns pre-computed complexity metrics without altering any state on the ScrumDo board. It is a pure read operation that retrieves existing analytical data. The deterministic nature (no LLM involvement) and passive retrieval confirm no side effects or destructive potential. Blast radius is minimal—misuse yields only incorrect information consumption, not data loss or unwanted actions.
From the tool's definition Tool name contains 'get_' prefix and description states it 'Return[s]' a complexity score and breakdown—indicating data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Return the deterministic (no-LLM) complexity score + breakdown. It is categorised as a Read tool in the Scrumdo MCP Server, which means it retrieves data without modifying state.
Register the Scrumdo MCP server in PolicyLayer and add a rule for get_spec_complexity: 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.
get_spec_complexity is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_spec_complexity 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 get_spec_complexity. 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.
get_spec_complexity 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 →