AI agents use memory_import to create or update resources in Jt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jt environment.
This tool creates or modifies data in a reversible manner. The merge mode adds to existing knowledge graph data, and replace mode overwrites it—both are Write operations. While replace mode approaches destructiveness, the operation targets a structured data store (knowledge graph) rather than irreversibly deleting files or records, and the data can be recovered or reimported.
From the tool's definition Tool description explicitly states 'Import a knowledge graph from JSON' with options to 'add to existing data' (merge mode) or 'start fresh' (replace mode). The 'replace mode' capability modifies existing data structures.
Attacks that exploit this kind of access
Import a knowledge graph from JSON. Use merge mode to add to existing data, or replace mode to start fresh. It is categorised as a Write tool in the Jt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jt 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 Jt. 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 Jt MCP server (@houkasaurusrex/jt-mcp-server). 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 →