AI agents use memory_import to create or update resources in Cortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cortex environment.
The tool imports data into Cortex's persistent memory system. This is a Write operation because it creates or modifies stored memories/notes in the Obsidian vault. Severity is high because malicious or erroneous imports could contaminate Claude's long-term memory with false information, incorrect decisions, or corrupted preferences, affecting all future sessions.
From the tool's definition Tool name 'memory_import' and sibling tools all operate on persistent memory storage (Obsidian vault, markdown notes). Import operations create or modify stored data.
Documented attack patterns abuse exactly the kind of access memory_import 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_import:
{
"version": "1",
"default": "deny",
"tools": {
"memory_import": {
"limits": [
{
"counter": "memory_import_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}memory_import stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
memory_import. It is categorised as a Write tool in the Cortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cortex MCP server in PolicyLayer and add a rule for memory_import: 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_import is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the memory_import 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_import. 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_import 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.