AI agents call clear_graph to permanently remove resources in Graphiti MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'clear_graph' indicates deletion of potentially large datasets without the ability to restore them. While the description is empty (lowering confidence slightly), the function name and server context (Neo4j knowledge graph storage) make it clear this is a destructive operation. This is more severe than Write (which is reversible) and qualifies as Destructive.
From the tool's definition Tool name 'clear_graph' strongly suggests irreversible deletion of graph data. Combined with server purpose (stores entities/relationships in Neo4j knowledge graphs), this tool likely wipes an entire graph—a non-reversible operation affecting all stored…
Documented attack patterns abuse exactly the kind of access clear_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Graphiti MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_graph:
{
"version": "1",
"default": "deny",
"hide": [
"clear_graph"
]
}clear_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.
clear_graph. It is categorised as a Destructive tool in the Graphiti MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Graphiti MCP Server MCP server in PolicyLayer and add a rule for clear_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 Graphiti MCP Server. Nothing to install.
clear_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 clear_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 clear_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.
clear_graph is provided by the Graphiti MCP Server MCP server (rawr-ai/mcp-graphiti). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Graphiti MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Graphiti MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.