AI agents call memento_get_project_state to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves project state information (vision, milestones, blockers, tech_debt, decisions, sprint) with no side effects. It is explicitly a 'get' operation that queries existing data. While the Memento system is designed for autonomous intelligence and goal enforcement, this specific tool only reads state; it does not execute actions, modify data, delete data, or move money.
From the tool's definition Tool name contains 'get' and description states 'Get the full project state' — retrieves data without modification. Marked as [DEPRECATED] indicating it is a legacy read operation.
Attacks that exploit this kind of access
[DEPRECATED] Get the full project state (vision, milestones, blockers, tech_debt, decisions, sprint). It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_get_project_state: 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 Memento. Nothing to install.
memento_get_project_state 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 memento_get_project_state 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 memento_get_project_state. 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.
memento_get_project_state is provided by the Memento MCP server (joyciakira/memento). 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 →