delete_observations

THE RISK

Critical Risk

Why delete_observations needs a policy

This tool permanently removes data (observations) from the knowledge graph without the possibility of reversal. Although it operates on individual observations rather than entire entities, the persistent nature of the knowledge graph means deleted observations cannot be recovered. This qualifies as a Destructive action rather than Write because deletion is irreversible.

From the tool's definition The tool name is 'delete_observations' and description states it will 'Delete specific observations from entities in the knowledge graph.' The verb 'delete' combined with the action of removing data from persistent storage indicates an irreversible operation.

Documented attack patterns abuse exactly the kind of access delete_observations gives an agent:

POLICY

How to control delete_observations

PolicyLayer is an MCP gateway — it sits between your AI agents and Knowledge Graph Memory Server, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_observations:

policy.json

{
  "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.

Create a free account and register Knowledge Graph Memory Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Knowledge Graph Memory Server tools

Destructive delete_entities Delete multiple entities and their associated relations from the knowledge graph Destructive delete_relations Delete multiple relations from the knowledge graph Write add_observations Add new observations to existing entities in the knowledge graph Write create_entities Create multiple new entities in the knowledge graph Write create_relations Create multiple new relations between entities in the knowledge graph. Relations should be Write update_entities Update multiple existing entities in the knowledge graph Write update_relations Update multiple existing relations in the knowledge graph Read read_graph Read the entire knowledge graph

All 11 Knowledge Graph Memory Server tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Knowledge Graph Memory Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about delete_observations

What does the delete_observations tool do? +

Delete specific observations from entities in the knowledge graph. It is categorised as a Destructive tool in the Knowledge Graph Memory Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_observations? +

Register the Knowledge Graph Memory Server 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 Knowledge Graph Memory Server. Nothing to install.

What risk level is delete_observations? +

delete_observations is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_observations? +

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.

How do I block delete_observations completely? +

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.

What MCP server provides delete_observations? +

delete_observations is provided by the Knowledge Graph Memory Server MCP server (itseasy21/mcp-knowledge-graph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Knowledge Graph Memory Server tool call.

Start from Knowledge Graph Memory Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →