AI agents call memory_project_snapshot 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 query/retrieval operation that gathers and presents existing information from the personal memory system. It has no side effects, cannot modify data, and is explicitly designed for informational purposes at the start of a session.
From the tool's definition Tool retrieves project data ('snapshot', 'recent activity', 'active goals', 'recent decisions', 'open threads', 'learned techniques') without modifying or deleting information.
Attacks that exploit this kind of access
Get a quick project snapshot: recent activity, active goals, recent decisions, open threads, and learned techniques. Use at start of a project session. 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_project_snapshot: 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_project_snapshot 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_project_snapshot 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_project_snapshot. 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_project_snapshot 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 →