AI agents call memory_graph to retrieve information from Cortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the server's function (persistent memory storage in Obsidian vault) and sibling tools that include audit, recall, and list operations, 'memory_graph' most likely retrieves or inspects graph metadata without modification. The lack of destructive naming patterns (no 'delete', 'drop', 'purge') and alignment with query-oriented siblings suggests this is a Read operation.
From the tool's definition Tool name 'memory_graph' with no description provided; sibling tools include 'memory_graph_audit' and 'memory_graph_rebuild' which suggest querying/inspecting graph structure.
Documented attack patterns abuse exactly the kind of access memory_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cortex, and nothing reaches the server without passing your rules. This is the rule we recommend for memory_graph:
{
"version": "1",
"default": "deny",
"tools": {
"memory_graph": {}
}
}memory_graph is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
memory_graph. It is categorised as a Read tool in the Cortex MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for memory_graph: 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 Cortex. Nothing to install.
memory_graph 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_graph 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_graph. 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_graph is provided by the Cortex MCP server (tt-wang/memem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Cortex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Cortex tools catalogued and risk-classified — across an index of 42,500+ MCP servers.