AI agents call get_loop_state 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 retrieves durable memory state associated with a loop without modifying, deleting, or executing external operations. It is a data retrieval operation with no side effects, fitting the Read category. Severity is low since reading internal loop state poses minimal risk even if exposed to an AI agent.
From the tool's definition Tool name 'get_loop_state' and description 'Read a loop's durable cross-run memory' explicitly use the verb 'Read' and indicate a retrieval-only operation.
Attacks that exploit this kind of access
Read a loop's durable cross-run memory (LoopState §2.12):. 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_loop_state: 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_loop_state 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_loop_state 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_loop_state. 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_loop_state 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 →