browse_stories

THE RISK

Low Risk

Why browse_stories needs a policy

This tool queries and retrieves Hacker News story data (stories, scores, comments, metadata) with no side effects, no data modification, and no code execution. It is a read-only retrieval operation on public content. Severity is low because misuse would only expose already-public Hacker News data, with minimal blast radius or harm potential.

From the tool's definition Tool name 'browse_stories' and description 'Browse Hacker News stories by type. Returns story list with scores, comments, and metadata.' indicate data retrieval only.

Documented attack patterns abuse exactly the kind of access browse_stories gives an agent:

POLICY

How to control browse_stories

PolicyLayer is an MCP gateway — it sits between your AI agents and HN-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browse_stories:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browse_stories": {}
  }
}

browse_stories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register HN-MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More HN-MCP tools

Read get_story_details Get a Hacker News story with its comments. Fetches full story content and comment threads. Read hn_explain Get explanations of Hacker News terms, culture, and conventions. Read search_hn Search Hacker News stories and comments. Returns matching content with relevance scores. Read user_analysis Analyze a Hacker News user

All 5 HN-MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browse_stories

What does the browse_stories tool do? +

Browse Hacker News stories by type. Returns story list with scores, comments, and metadata. It is categorised as a Read tool in the HN-MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browse_stories? +

Register the HN- MCP server in PolicyLayer and add a rule for browse_stories: 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 HN-MCP. Nothing to install.

What risk level is browse_stories? +

browse_stories is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit browse_stories? +

Yes. Add a rate_limit block to the browse_stories 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 browse_stories completely? +

Set action: deny in the PolicyLayer policy for browse_stories. 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 browse_stories? +

browse_stories is provided by the HN- MCP server (karanb192/hn-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every HN-MCP tool call.

Start from HN-MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →