get_class_details
AI agents call get_class_details to retrieve information from Remote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and pattern of sibling tools indicate this retrieves data without side effects. No indication of write, execute, destructive, or financial capabilities. Low severity due to empty description reducing confidence; tool appears to query game data within a Cloudflare Workers deployment context.
From the tool's definition Tool name 'get_class_details' suggests retrieval of information about game classes. Sibling tools (get_entry, get_monster_stats, get_spell_details) are all read operations. Description is empty, limiting evidence.
Attacks that exploit this kind of access
get_class_details. It is categorised as a Read tool in the Remote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Remote MCP Server MCP server in PolicyLayer and add a rule for get_class_details: 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 Remote MCP Server. Nothing to install.
get_class_details 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 get_class_details 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 get_class_details. 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.
get_class_details is provided by the Remote MCP Server MCP server (robertsapunarich/mcp-ose). 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 →