AI agents call memory_facts to retrieve information from Exocortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that retrieves structured facts from the memory system. However, the severity is elevated to 'high' because the facts being queried include sensitive information such as 'ports, versions, config values, dependencies' - infrastructure and configuration details that could be exploited if an AI agent misuses this tool to extract operational secrets, expose system topology, or gather…
From the tool's definition Tool name 'memory_facts' with description 'Query structured subject-predicate-object facts' indicates data retrieval.
Attacks that exploit this kind of access
Query structured subject-predicate-object facts. Use for precise lookups: ports, versions, config values, dependencies. It is categorised as a Read tool in the Exocortex MCP Server, which means it retrieves data without modifying state.
Register the Exocortex MCP server in PolicyLayer and add a rule for memory_facts: 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 Exocortex. Nothing to install.
memory_facts 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 memory_facts 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 memory_facts. 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.
memory_facts is provided by the Exocortex MCP server (shawnhack/exocortex). 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 →