load_rulebook
AI agents call load_rulebook 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.
The tool appears designed to load rulebook data for querying, which is a read-only operation. The server explicitly mentions RAG (Retrieval-Augmented Generation) capabilities for rulebooks. Given the D&D campaign management context and the presence of query-oriented sibling tools, this is most likely a data retrieval function with no side effects.
From the tool's definition Tool name 'load_rulebook' combined with server context indicating 'query personal PDF rulebooks using RAG capabilities' and sibling tools like 'ask_books' suggest data retrieval. No description provided, which lowers confidence slightly.
Attacks that exploit this kind of access
load_rulebook. 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 load_rulebook: 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.
load_rulebook 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 load_rulebook 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 load_rulebook. 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.
load_rulebook 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 →