Remove a feed and all its entries.
AI agents call delete_feed_tool to permanently remove resources in MCP Feed Reader — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly removes both a feed subscription and all associated cached entries from the SQLite backend. This is a destructive operation that cannot be undone through normal means. While the blast radius is somewhat limited to feed data rather than critical business systems, the permanent loss of accumulated feed history and entries justifies 'high' severity.
From the tool's definition Tool name includes 'delete' and description states 'Remove a feed and all its entries' – this permanently deletes data without possibility of reversal.
Attacks that exploit this kind of access
Remove a feed and all its entries. It is categorised as a Destructive tool in the MCP Feed Reader MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for delete_feed_tool: 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 MCP Feed Reader. Nothing to install.
delete_feed_tool is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_feed_tool 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 delete_feed_tool. 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.
delete_feed_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). 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 →