Erinnerungen einer bestimmten Kategorie abrufen
AI agents call recall_category to retrieve information from Baby-SkyNet 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 memories filtered by category from the persistent memory system. It performs a read-only operation on the SQL database and vector store, returning existing data with no side effects, no code execution, and no data modification. The sibling tool context (get_recent_memories, list_categories, get_analysis_result) confirms this is part of a read-focused memory retrieval API.
From the tool's definition Tool name 'recall_category' and description 'Erinnerungen einer bestimmten Kategorie abrufen' (retrieve memories of a certain category) indicate data retrieval without modification.
Attacks that exploit this kind of access
Erinnerungen einer bestimmten Kategorie abrufen. It is categorised as a Read tool in the Baby-SkyNet MCP Server, which means it retrieves data without modifying state.
Register the Baby-SkyNet MCP server in PolicyLayer and add a rule for recall_category: 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 Baby-SkyNet. Nothing to install.
recall_category 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 recall_category 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 recall_category. 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.
recall_category is provided by the Baby-SkyNet MCP server (spie-mkroehn/baby-skynet). 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 →