View the version history of a specific keypath.
AI agents call memory_history to retrieve information from Memstate AI - Agent Memory System without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays version history information, which is a query operation with no side effects. It does not create, modify, delete, or execute operations—it only provides visibility into past states of memory. The blast radius of misuse is minimal since reading history cannot compromise system integrity or cause data loss.
From the tool's definition Tool name 'memory_history' and description 'View the version history of a specific keypath' indicate read-only retrieval of historical data without modification.
Attacks that exploit this kind of access
View the version history of a specific keypath. It is categorised as a Read tool in the Memstate AI - Agent Memory System MCP Server, which means it retrieves data without modifying state.
Register the Memstate AI - Agent Memory System 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 Memstate AI - Agent Memory System. 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 Memstate AI - Agent Memory System MCP server (memstate-ai/memstate-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 →