follow_feed · Feedbagel MCP Server MCP: Risk & Policy

WHAT IT DOES

What follow_feed does on Feedbagel MCP Server

AI agents use follow_feed to create or update resources in Feedbagel MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feedbagel MCP Server environment.

WHY IT NEEDS A POLICY

Why follow_feed needs a policy

The tool creates a new subscription or feed association for the user. This is a Write operation because it modifies user data (their feed list) in a reversible manner—the user can later 'detach' or remove the feed. It is not Destructive (can be undone), not Execute (does not run arbitrary code), not Financial (no money involved), and not Read (has side effects).

From the tool's definition Tool description states 'Add a feed to the user', which is a create/modify operation. This is confirmed by the action verb 'follow' (subscribe/add) and the presence of sibling destructive tools like 'delete_webhook' and 'detach_feed_from_webhook' that suggest…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

follow_feed Rate-limited

follow_feed stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "follow_feed": {
      "limits": [
        {
          "counter": "follow_feed_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Feedbagel MCP Server, so you can run agents against it safely.

FAQ

Questions about follow_feed

What does the follow_feed tool do? +

Add a feed to the user. It is categorised as a Write tool in the Feedbagel MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on follow_feed? +

Register the Feedbagel MCP Server MCP server in PolicyLayer and add a rule for follow_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.

What risk level is follow_feed? +

follow_feed is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit follow_feed? +

Yes. Add a rate_limit block to the follow_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.

How do I block follow_feed completely? +

Set action: deny in the PolicyLayer policy for follow_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.

What MCP server provides follow_feed? +

follow_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.