list_outputs

THE RISK

Low Risk

Why list_outputs needs a policy

This tool retrieves directory contents and file metadata without any side effects, creation, modification, deletion, or execution of code. It is a straightforward read operation querying the output directory state.

From the tool's definition Tool description states 'List all rendered clip files in the output directory' - a pure query/list operation with no modification or execution capability. Returns metadata (file sizes and dates) only.

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

POLICY

How to control list_outputs

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

policy.json

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

list_outputs 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 Podcli — 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 Podcli tools

Execute parse_transcript Parse a raw speaker-labeled plain text transcript into word-level timestamps. Input format Execute batch_create_clips STEP 3 — Export multiple clips at once as finished vertical shorts.\n\n Execute transcribe_podcast STEP 1 — Transcribe a podcast video/audio file. This is typically the first tool you call. Write create_clip STEP 3 — Export a single clip as a finished vertical short (1080x1920, 9:16).\n\n Write import_transcript Import an external transcript (e.g. from a transcription service) into the UI. Skips Whisp Write knowledge_base Read or manage the podcli knowledge base. These are .md files that provide context about t Write manage_assets Register and manage reusable assets (logos, videos). Registered assets can be referenced b Write manage_presets Save, load, list, or delete rendering presets. Presets store caption_style, crop_strategy,

All 17 Podcli 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 list_outputs

What does the list_outputs tool do? +

List all rendered clip files in the output directory with file sizes and dates. It is categorised as a Read tool in the Podcli MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_outputs? +

Register the Podcli MCP server in PolicyLayer and add a rule for list_outputs: 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 Podcli. Nothing to install.

What risk level is list_outputs? +

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

Can I rate-limit list_outputs? +

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

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

list_outputs is provided by the Podcli MCP server (nmbrthirteen/podcli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Podcli tool call.

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

CHECK YOUR STACK →