AI agents call get_memory_by_agent to retrieve information from MCP RAG 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 associated with a specific agent without modifying, deleting, or executing anything. It is a straightforward data retrieval operation consistent with the 'get' pattern. The severity is low because exposure only risks information disclosure of the agent's stored memory, not data loss, code execution, or financial impact.
From the tool's definition Tool name 'get_memory_by_agent' and description 'Get all memory entries for a specific agent' indicate a retrieval operation with no side effects. The verb 'Get' is explicitly listed as a Read category operation.
Attacks that exploit this kind of access
Get all memory entries for a specific agent. It is categorised as a Read tool in the MCP RAG MCP Server, which means it retrieves data without modifying state.
Register the MCP RAG MCP server in PolicyLayer and add a rule for get_memory_by_agent: 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 MCP RAG. Nothing to install.
get_memory_by_agent 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 get_memory_by_agent 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 get_memory_by_agent. 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.
get_memory_by_agent is provided by the MCP RAG MCP server (santis84/mcp-rag). 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 →