Scan the library folder for new PDF/Markdown files and index them.
AI agents call scan_library to retrieve information from DM20 Protocol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from the file system and builds an index—a non-destructive read operation. While 'scan' might suggest broader capabilities, the explicit scope (new PDF/Markdown files in a library folder) and the context of a D&D campaign management system (personal rulebooks via RAG) confirm this is a file discovery and cataloging operation.
From the tool's definition The tool 'scan_library' performs a scanning and indexing operation on existing files in a library folder. The description indicates it reads PDF/Markdown files and indexes them (creates metadata/search indices), with no modification or deletion of the source…
Attacks that exploit this kind of access
Scan the library folder for new PDF/Markdown files and index them. It is categorised as a Read tool in the DM20 Protocol MCP Server, which means it retrieves data without modifying state.
Register the DM20 Protocol MCP server in PolicyLayer and add a rule for scan_library: 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 DM20 Protocol. Nothing to install.
scan_library 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 scan_library 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 scan_library. 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.
scan_library is provided by the DM20 Protocol MCP server (polloinfilzato/dm20-protocol). 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 →