Copy memory entities and their relations from one project to another
AI agents use copy_memory to create or update resources in Xgmem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Xgmem environment.
The copy operation transfers data between projects, which constitutes data creation/modification in the destination project. While the action is reversible (copied data can be deleted), it definitively modifies project state. This is not Read (it has side effects), not Destructive (copying is reversible), and not Execute/Financial/Other.
From the tool's definition Tool description states it 'Copy[s] memory entities and their relations from one project to another' — this creates or duplicates data in a target project, modifying its state.
Documented attack patterns abuse exactly the kind of access copy_memory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xgmem, and nothing reaches the server without passing your rules. This is the rule we recommend for copy_memory:
{
"version": "1",
"default": "deny",
"tools": {
"copy_memory": {
"limits": [
{
"counter": "copy_memory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}copy_memory 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.
Copy memory entities and their relations from one project to another. It is categorised as a Write tool in the Xgmem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Xgmem MCP server in PolicyLayer and add a rule for copy_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 Xgmem. Nothing to install.
copy_memory 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 copy_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 copy_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.
copy_memory is provided by the Xgmem MCP server (meetdhanani17/xgmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Xgmem, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Xgmem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.