ask_books
AI agents call ask_books 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.
Despite the empty description, the naming pattern ('ask_books') combined with the server's stated RAG capability for querying 'personal PDF rulebooks' strongly suggests this is a Read operation that retrieves information from stored game rule documents. This would be a simple data lookup with no side effects. Confidence is moderate due to the missing description, but the semantic intent is clear.
From the tool's definition Tool name 'ask_books' with empty description suggests querying stored rulebook PDFs using RAG capabilities mentioned in server description. The 'ask' verb indicates information retrieval rather than modification.
Attacks that exploit this kind of access
ask_books. 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 ask_books: 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.
ask_books 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 ask_books 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 ask_books. 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.
ask_books 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 →