party_get_prefetch
AI agents call party_get_prefetch 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 retrieve or preload party information for D&D campaign management. 'Get' operations are typically read-only, and 'prefetch' suggests caching/preparing data for display. Without description, confidence is moderate, but the pattern matches Read category (retrieve data without side effects). No evidence of mutation, deletion, code execution, or financial impact.
From the tool's definition Tool name 'party_get_prefetch' indicates a retrieval operation; 'get' and 'prefetch' are characteristic of read-only data fetching patterns.
Attacks that exploit this kind of access
party_get_prefetch. 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 party_get_prefetch: 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.
party_get_prefetch 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 party_get_prefetch 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 party_get_prefetch. 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.
party_get_prefetch 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 →