AI agents call memory_history to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves historical versions of memory entries. It has no side effects, makes no modifications, executes no code, and does not delete data. It is a pure read operation that queries existing versioned memory data. The blast radius of misuse is minimal—an agent with this tool can only view historical versions, not alter or delete them.
From the tool's definition Tool retrieves and returns version history data without modifying, deleting, or executing any code. Description states 'Retrieve version history' which is a read operation.
Attacks that exploit this kind of access
Retrieve version history for a memory entry. Returns versions newest-first. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for memory_history: 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 Memory. Nothing to install.
memory_history 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_history 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_history. 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_history is provided by the Memory MCP server (joshdougall/memory-mcp). 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 →