Remove a feed from the user
AI agents call unfollow_feed to permanently remove resources in Feedbagel MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Unfollowing a feed removes the subscription record for the user. This is effectively a deletion action (removing a follow relationship), which is typically not reversible without explicitly re-following the feed. While not catastrophic in blast radius, it irreversibly removes the feed association, placing it in the Destructive category over Write.
From the tool's definition 'Remove a feed from the user' — the tool removes/unfollows a feed subscription, which is a deletion of the subscription relationship.
Attacks that exploit this kind of access
Remove a feed from the user. It is categorised as a Destructive tool in the Feedbagel MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Feedbagel MCP Server MCP server in PolicyLayer and add a rule for unfollow_feed: 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 Feedbagel MCP Server. Nothing to install.
unfollow_feed 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 unfollow_feed 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 unfollow_feed. 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.
unfollow_feed is provided by the Feedbagel MCP Server MCP server (prototypr/feedbagel-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 →