AI agents call memory_ping 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 tool performs a health check that queries and returns information about the system state (memory counts, entity/tag statistics, uptime). It is purely observational with no side effects, modifications, or data destruction. It fits the 'Read' category as it retrieves system metrics for diagnostic purposes only.
From the tool's definition Tool name 'memory_ping' and description 'Health check — returns memory counts, entity/tag stats, and uptime' indicate a read-only diagnostic operation that retrieves and reports system statistics without modifying any data.
Attacks that exploit this kind of access
Health check — returns memory counts, entity/tag stats, and uptime. 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_ping: 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_ping 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_ping 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_ping. 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_ping 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 →