list_product_files
AI agents call list_product_files to retrieve information from Source Coop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries file information without modifying, deleting, or executing anything. It falls squarely into the Read category with low severity due to operating on publicly available geospatial data with no side effects or blast radius.
From the tool's definition Tool name 'list_product_files' indicates retrieval of a file listing. Server description confirms the tool is for 'discovering and accessing' public geospatial data, with sibling tools being 'list_accounts', 'list_products', and 'search', all of which are…
Attacks that exploit this kind of access
list_product_files. It is categorised as a Read tool in the Source Coop MCP Server, which means it retrieves data without modifying state.
Register the Source Coop MCP server in PolicyLayer and add a rule for list_product_files: 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 Source Coop. Nothing to install.
list_product_files 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 list_product_files 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 list_product_files. 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.
list_product_files is provided by the Source Coop MCP server (yharby/source-coop-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 →