AI agents use import_memories to create or update resources in Tages — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tages environment.
This tool creates or modifies memory records in the persistent storage system. While imports can overwrite existing memories, they are reversible operations (data can be re-imported, updated, or corrected in subsequent operations). This is a Write operation rather than Destructive because the changes are not irreversible — memories can be subsequently modified or corrected.
From the tool's definition Tool description states it "Import memories from a JSON array or markdown file content" and "Handles duplicates with skip/overwrite/merge strategies" — indicating creation and modification of stored memory data.
Attacks that exploit this kind of access
Import memories from a JSON array or markdown file content. Handles duplicates with skip/overwrite/merge strategies. It is categorised as a Write tool in the Tages MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tages MCP server in PolicyLayer and add a rule for import_memories: 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 Tages. Nothing to install.
import_memories 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 import_memories 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 import_memories. 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.
import_memories is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →