AI agents call memory_chain_get to retrieve information from Mementos 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 existing memory data without creating, modifying, deleting, or executing any operations. It is a straightforward read-only accessor that fetches structured data based on a group ID parameter. The low severity reflects minimal blast radius — even if misused by an agent, it only accesses data without causing harm or irreversible changes.
From the tool's definition Tool name contains 'get' and description states 'Retrieve an ordered memory chain/sequence' with 'Returns all steps in order' — purely a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieve an ordered memory chain/sequence by group ID. Returns all steps in order. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_chain_get: 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 Mementos. Nothing to install.
memory_chain_get 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_chain_get 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_chain_get. 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_chain_get is provided by the Mementos MCP server (@hasna/mementos). 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 →