Download the open-access PDF of a PhilArchive record and save it into the server
AI agents use fetch_pdf to create or update resources in Philosophy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Philosophy environment.
The tool downloads a remote PDF and saves/writes it to the server's local storage. This is a Write operation (creates new data on the server). It is reversible in principle (the file could be deleted), so it does not qualify as Destructive. The blast radius is medium — an agent could fill disk space or save unexpected content, but the scope is limited to philosophy PDFs from a known open-access source.
From the tool's definition Download the open-access PDF of a PhilArchive record and save it into the server
Attacks that exploit this kind of access
Download the open-access PDF of a PhilArchive record and save it into the server. It is categorised as a Write tool in the Philosophy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Philosophy MCP server in PolicyLayer and add a rule for fetch_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 Philosophy. Nothing to install.
fetch_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 fetch_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 fetch_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.
fetch_pdf is provided by the Philosophy MCP server (sea9401/philosophy-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 →