AI agents call store_list to retrieve information from Willow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing data from storage without creating, modifying, deleting, or executing any operations. It is a straightforward query operation with no blast radius beyond exposing stored information. The low severity reflects the read-only nature and the availability of alternative search operations for large datasets.
From the tool's definition Tool name 'store_list' and description 'Return every record in a collection' indicate data retrieval with no modification or side effects. The note to 'Use store_search for large collections' reinforces it is a read-only operation.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Return every record in a collection. Use store_search for large collections —. It is categorised as a Read tool in the Willow MCP Server, which means it retrieves data without modifying state.
Register the Willow MCP server in PolicyLayer and add a rule for store_list: 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 Willow. Nothing to install.
store_list 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 store_list 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 store_list. 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.
store_list is provided by the Willow MCP server (rudi193-cmd/willow-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 →