This record as markdown: /tools/20alexl-claude-engram/memory.md
What memory does on Claude Engram
AI agents call memory to retrieve information from Claude Engram without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why memory is rated Low
Although the description is empty, the naming and server context strongly indicate this tool retrieves memory data from the session history. The server explicitly describes mining, tracking, and searching—all read operations. No evidence suggests data modification, deletion, or execution of external operations. However, lowered confidence (0.6 rather than 0.8+) due to the lack of an explicit tool description.
From the tool's definition Tool named 'memory' on a server described as providing 'persistent memory and session intelligence' that 'auto-tracks mistakes, decisions, and context' and 'mines your full session history for patterns, predictions, and cross-session search.' The empty…
Attacks that exploit this kind of access
The rule that runs memory safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Engram, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For memory, this is the rule to start with:
memory is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Engram, apply this rule, and every memory call is checked against it from then on.
Questions about memory
memory is a read tool on the Claude Engram MCP server. It is categorised as a Read tool in the Claude Engram MCP Server, which means it retrieves data without modifying state.
Register the Claude Engram MCP server in PolicyLayer and add a rule for memory: 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 Claude Engram. Nothing to install.
memory 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 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. 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 is provided by the Claude Engram MCP server (20alexl/claude-engram). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Engram, and thousands of servers like it.
This server
Across the catalogue