delete_observations
AI agents call delete_observations to permanently remove resources in DAI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes observations from the persistent memory graph. Even though the description is empty, the name combined with context that this is a Neo4j-backed persistent memory system makes it clear this performs an unrecoverable destructive action. Deletion operations cannot be undone and represent the highest risk category aside from financial operations.
From the tool's definition Tool name 'delete_observations' indicates irreversible deletion. The server stores persistent memory in Neo4j, and deletion of observations removes data that cannot be undone.
Attacks that exploit this kind of access
delete_observations. It is categorised as a Destructive tool in the DAI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the DAI 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 DAI 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 DAI MCP Server MCP server (patgpt/dai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →