Return a domain-keyed memory bundle: curated wiki entries + recent reflections + prior outcomes for a named domain. Use to specialize a sub-agent
AI agents call knowledge_expert to retrieve information from Ralph Hero without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves specialized domain knowledge from memory/storage for the purpose of informing a sub-agent. There are no side effects, data modifications, deletions, executions, or financial implications described. It is purely informational/consultative, making it a Read operation with low risk even if misused by an agent—at worst it would retrieve irrelevant or excessive information.
From the tool's definition Tool returns/retrieves data ("domain-keyed memory bundle: curated wiki entries + recent reflections + prior outcomes") with no modification or deletion capability mentioned. The verb "Return" and passive retrieval nature indicate query-like behavior.
Attacks that exploit this kind of access
Return a domain-keyed memory bundle: curated wiki entries + recent reflections + prior outcomes for a named domain. Use to specialize a sub-agent. It is categorised as a Read tool in the Ralph Hero MCP Server, which means it retrieves data without modifying state.
Register the Ralph Hero MCP server in PolicyLayer and add a rule for knowledge_expert: 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 Ralph Hero. Nothing to install.
knowledge_expert 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 knowledge_expert 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 knowledge_expert. 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.
knowledge_expert is provided by the Ralph Hero MCP server (ralph-hero-mcp-server). 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 →