Role-aware retrieval over the knowledge base. Fans out one rerank-enabled hybrid.search() per memory tier in the role
AI agents call knowledge_recall 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 performs data retrieval only. The 'rerank-enabled hybrid search' pattern is a read-only operation that queries and ranks existing knowledge base entries across memory tiers. There are no side effects, data modifications, code execution, or destructive operations. The role-aware aspect is a permission/filtering mechanism, not a capability that changes the action category from Read.
From the tool's definition Tool description states 'retrieval over the knowledge base' and 'hybrid.search()' - these are query/search operations with no modification capability mentioned. No create, update, delete, execute, or financial operations are indicated.
Attacks that exploit this kind of access
Role-aware retrieval over the knowledge base. Fans out one rerank-enabled hybrid.search() per memory tier in the role. 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_recall: 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_recall 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_recall 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_recall. 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_recall 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 →