AI agents use save_pdf to create or update resources in Md24de — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Md24de environment.
The tool creates or writes PDF files to persistent storage, making it a Write category action. Severity is medium because misuse could fill disk space, overwrite user files, or store sensitive utility/consumption data in unintended locations, but it is reversible (files can be deleted). Confidence is 0.85 rather than higher due to empty description providing no explicit confirmation of side effects.
From the tool's definition Tool name 'save_pdf' indicates file creation/storage operation. Server context shows it handles utility consumption reports and PDF downloads, suggesting this tool persists files to storage.
Attacks that exploit this kind of access
save_pdf. It is categorised as a Write tool in the Md24de MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Md24de MCP server in PolicyLayer and add a rule for save_pdf: 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 Md24de. Nothing to install.
save_pdf 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 save_pdf 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 save_pdf. 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.
save_pdf is provided by the Md24de MCP server (volsch/md24de-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 →