Remove an annotation that is no longer relevant — e.g. a bug that was fixed, a constraint that no longer applies, or a note on a deleted file/symbol. Use get_annotations first to find the annotation ID.
AI agents call delete_annotation to permanently remove resources in Local Rag — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes annotations from the codebase metadata. While the blast radius is moderate—annotations are metadata, not code or production systems—the action is irreversible. An agent instructed to clean up annotations could indiscriminately delete important context (bug notes, constraints, documentation). This fits the Destructive category because deletion cannot be undone without recovery mechanisms.
From the tool's definition Tool name 'delete_annotation' and description 'Remove an annotation' indicate irreversible deletion of data (annotations stored in the system).
Documented attack patterns abuse exactly the kind of access delete_annotation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_annotation:
{
"version": "1",
"default": "deny",
"hide": [
"delete_annotation"
]
} delete_annotation 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.
Remove an annotation that is no longer relevant — e.g. a bug that was fixed, a constraint that no longer applies, or a note on a deleted file/symbol. Use get_annotations first to find the annotation ID. It is categorised as a Destructive tool in the Local Rag MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Local Rag MCP server in PolicyLayer and add a rule for delete_annotation: 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 Local Rag. Nothing to install.
delete_annotation 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_annotation 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_annotation. 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_annotation is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, 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.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.