列出指定目录下的所有PDF文件
AI agents call list_pdfs_in_directory to retrieve information from Custom PDF MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about PDF files in a directory without modifying, deleting, or executing anything. It is a read-only operation that queries the filesystem for metadata (filenames and locations). The blast radius is minimal since it only exposes file presence information within the specified directory, posing no destructive or execution risk.
From the tool's definition Tool name 'list_pdfs_in_directory' and description '列出指定目录下的所有PDF文件' (lists all PDF files in specified directory) indicate directory enumeration and file listing operations.
Attacks that exploit this kind of access
列出指定目录下的所有PDF文件. It is categorised as a Read tool in the Custom PDF MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Custom PDF MCP Server MCP server in PolicyLayer and add a rule for list_pdfs_in_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 Custom PDF MCP Server. Nothing to install.
list_pdfs_in_directory is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_pdfs_in_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.
Set action: deny in the PolicyLayer policy for list_pdfs_in_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.
list_pdfs_in_directory is provided by the Custom PDF MCP Server MCP server (waicy/-pdf-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 →