DELETE specific OBSERVATIONS from entities while preserving the entity, its relationships, and tags. Use for correcting errors or removing outdated facts without deleting the entire entity.
AI agents call delete_observations to permanently remove resources in KnowledgeGraph MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes observations (stored facts/data) from the knowledge graph. While it preserves the entity itself, the deletion of observations is irreversible and constitutes data destruction. The high severity reflects that an AI agent could maliciously or erroneously purge important historical facts or observations that cannot be recovered, potentially corrupting the knowledge base.
From the tool's definition Tool name includes 'delete', description states 'DELETE specific OBSERVATIONS from entities' and clarifies this removes data 'without deleting the entire entity', indicating irreversible removal of stored information.
Risk signalsBulk/mass operation — affects multiple targets
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 KnowledgeGraph MCP Server, 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 while preserving the entity, its relationships, and tags. Use for correcting errors or removing outdated facts without deleting the entire entity. It is categorised as a Destructive tool in the KnowledgeGraph MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KnowledgeGraph MCP 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 KnowledgeGraph MCP Server. 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 KnowledgeGraph MCP Server MCP server (n-r-w/knowledgegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KnowledgeGraph MCP Server, 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.
11 KnowledgeGraph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.