Medium Risk

set_download_directory

Set the main local download folder for markdown files

Risk signalsAccepts file system path (directory)

Part of the Markdown Downloader server.

set_download_directory can modify Markdown Downloader data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE MARKDOWN DOWNLOADER →

Free to start. No card required.

AI agents use set_download_directory to create or modify resources in Markdown Downloader. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call set_download_directory repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Markdown Downloader.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_download_directory": {
      "limits": [
        {
          "counter": "set_download_directory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Markdown Downloader policy for all 5 tools.

Get this rule live on your own Markdown Downloader server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY MARKDOWN DOWNLOADER →

These attack patterns abuse exactly the kind of access set_download_directory gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so set_download_directory only ever does what you allow.

SECURE MARKDOWN DOWNLOADER →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the set_download_directory tool do? +

Set the main local download folder for markdown files. It is categorised as a Write tool in the Markdown Downloader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_download_directory? +

Register the Markdown Downloader MCP server in PolicyLayer and add a rule for set_download_directory: 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 Markdown Downloader. Nothing to install.

What risk level is set_download_directory? +

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

Can I rate-limit set_download_directory? +

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

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

set_download_directory is provided by the Markdown Downloader MCP server (dazeb/markdown-downloader). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Markdown Downloader tool call.

Deterministic rules across all 5 Markdown Downloader tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.