Download a binary file (PDF, image, ZIP, etc.) from a URL and save it to a local path.
AI agents use download_file to create or update resources in Markdown For Agents — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Markdown For Agents environment.
This tool fetches a remote file and writes it to the local filesystem. It creates/overwrites a local file, which is a Write action. The severity is medium because it can write arbitrary binary content (including ZIPs or executables) to a local path, but it does not execute code or irreversibly destroy existing data by itself.
From the tool's definition Download a binary file (PDF, image, ZIP, etc.) from a URL and save it to a local path.
Attacks that exploit this kind of access
Download a binary file (PDF, image, ZIP, etc.) from a URL and save it to a local path. It is categorised as a Write tool in the Markdown For Agents MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Markdown For Agents MCP server in PolicyLayer and add a rule for download_file: 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 For Agents. Nothing to install.
download_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the download_file 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.
Set action: deny in the PolicyLayer policy for download_file. 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.
download_file is provided by the Markdown For Agents MCP server (johnnyfoulds/markdown-for-agents-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →