Read the agent memory index (MEMORY.md) and optionally specific topic files. Call with no arguments to load only the lightweight index (cheap). Pass
AI agents call memory_read to retrieve information from Agent Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though memory_read only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Read the agent memory index (MEMORY.md) and optionally specific topic files. Call with no arguments to load only the lightweight index (cheap). Pass. It is categorised as a Read tool in the Agent Memory MCP Server, which means it retrieves data without modifying state.
Register the Agent Memory MCP server in PolicyLayer and add a rule for memory_read: 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 Agent Memory. Nothing to install.
memory_read 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_read 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_read. 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_read is provided by the Agent Memory MCP server (tverney/mcp-agent-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.