add_feed · Rss Feeds MCP: Risk & Policy

WHAT IT DOES

What add_feed does on Rss Feeds

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

WHY IT NEEDS A POLICY

Why add_feed needs a policy

Adding an RSS feed creates or modifies the system's feed configuration. This is a Write action (creates data reversibly) rather than Read (no side effects) or Destructive (cannot be undone). Severity is low because misconfiguration of RSS feeds poses minimal risk—feeds can be removed, and RSS content is typically public. No code execution, financial impact, or irreversible data loss is involved.

From the tool's definition Tool name 'add_feed' and description 'Add a new RSS feed' indicate creation of a new configuration entry. This is a reversible write operation—the feed can be removed (as evidenced by the sibling 'remove_feed' tool).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_feed Rate-limited

add_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": {
    "add_feed": {
      "limits": [
        {
          "counter": "add_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 Rss Feeds, so you can run agents against it safely.

FAQ

Questions about add_feed

What does the add_feed tool do? +

Add a new RSS feed with optional category. It is categorised as a Write tool in the Rss Feeds MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_feed? +

Register the Rss Feeds MCP server in PolicyLayer and add a rule for add_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 Rss Feeds. Nothing to install.

What risk level is add_feed? +

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

Can I rate-limit add_feed? +

Yes. Add a rate_limit block to the add_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 add_feed completely? +

Set action: deny in the PolicyLayer policy for add_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 add_feed? +

add_feed is provided by the Rss Feeds MCP server (lionkiii/rss-feeds-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.