Delete specific observations from entities in the project knowledge graph
AI agents call delete_observations to permanently remove resources in Xgmem — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (observations) from a persistent knowledge graph stored on disk. Once deleted, observations cannot be recovered through normal tool operations.
From the tool's definition Tool name is 'delete_observations' and description states it 'Delete[s] specific observations from entities in the project knowledge graph'. The verb 'delete' indicates irreversible removal of data.
Documented attack patterns abuse exactly the kind of access delete_observations 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 delete_observations:
{
"version": "1",
"default": "deny",
"hide": [
"delete_observations"
]
} delete_observations disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete specific observations from entities in the project knowledge graph. It is categorised as a Destructive tool in the Xgmem MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Xgmem MCP server in PolicyLayer and add a rule for delete_observations: 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.
delete_observations is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_observations 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 delete_observations. 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.
delete_observations 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.