Load the full input schema for a specific tool (required before first use). Returns parameter definitions, types, and usage info.
AI agents call load_tool_schema to retrieve information from Rpg without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns schema information about other tools—it reads and queries metadata without creating, modifying, executing, or deleting anything. It has no side effects on game state, player data, or persistence layer. The blast radius if misused by an AI agent is negligible since schema introspection alone cannot cause harm.
From the tool's definition Tool name 'load_tool_schema' and description 'Load the full input schema for a specific tool' indicates retrieval of metadata/documentation. Returns 'parameter definitions, types, and usage info' with no side effects mentioned.
Documented attack patterns abuse exactly the kind of access load_tool_schema gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rpg, and nothing reaches the server without passing your rules. This is the rule we recommend for load_tool_schema:
{
"version": "1",
"default": "deny",
"tools": {
"load_tool_schema": {}
}
}load_tool_schema is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load the full input schema for a specific tool (required before first use). Returns parameter definitions, types, and usage info. It is categorised as a Read tool in the Rpg MCP Server, which means it retrieves data without modifying state.
Register the Rpg MCP server in PolicyLayer and add a rule for load_tool_schema: 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 Rpg. Nothing to install.
load_tool_schema 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_tool_schema 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_tool_schema. 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_tool_schema is provided by the Rpg MCP server (mnehmos/mnehmos.rpg.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rpg, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
47 Rpg tools catalogued and risk-classified — across an index of 43,000+ MCP servers.