AI agents use create_pdf_summary to create or update resources in FastMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FastMCP environment.
The tool creates or generates a new PDF summary artifact. This is a reversible modification/creation operation (Write category). Severity is medium because unauthorized PDF creation could clutter storage or be used to generate misleading documents, but PDFs themselves are typically not destructive.
From the tool's definition Tool name 'create_pdf_summary' indicates generation/creation of a PDF document. The server description mentions 'PDF summary generation' as a core capability. Creation of files is a Write operation.
Attacks that exploit this kind of access
create_pdf_summary. It is categorised as a Write tool in the FastMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fast MCP server in PolicyLayer and add a rule for create_pdf_summary: 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 FastMCP. Nothing to install.
create_pdf_summary 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 create_pdf_summary 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 create_pdf_summary. 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.
create_pdf_summary is provided by the Fast MCP server (rutie345/fastmcp). 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 →