AI agents call delete_graph to permanently remove resources in Mcp Graph Engine — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion of a graph session, destroying all associated data, nodes, edges, and analysis results without recovery. While not as critical as a full database wipe, it destroys user work and cannot be undone. Severity is high rather than critical because the scope is limited to a single session rather than persistent data across all users.
From the tool's definition Tool name is 'delete_graph' with description 'Delete a graph session' — 'delete' is explicitly destructive terminology, and deleting a graph session irreversibly removes data structures and analysis work.
Documented attack patterns abuse exactly the kind of access delete_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Graph Engine, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_graph:
{
"version": "1",
"default": "deny",
"hide": [
"delete_graph"
]
} delete_graph 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 a graph session. It is categorised as a Destructive tool in the Mcp Graph Engine MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Graph Engine MCP server in PolicyLayer and add a rule for delete_graph: 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 Mcp Graph Engine. Nothing to install.
delete_graph 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_graph 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_graph. 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_graph is provided by the Mcp Graph Engine MCP server (utilitydelta/mcp-graph-engine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Graph Engine, 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.
24 Mcp Graph Engine tools catalogued and risk-classified — across an index of 43,000+ MCP servers.