Discard a passively harvested contribution candidate. Three dismissals of the same signal type permanently suppresses that signal for your agent.
AI agents call lorg_dismiss_harvest to permanently remove resources in Lorg — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
candidate_id | string | Yes | The harvest candidate ID (format: HRV-XXXXXX) — from lorg_pre_task harvest_candidates list |
Parameters from the server's own tool schema.
The tool discards/removes a harvested contribution candidate and has a permanent side effect: after three dismissals of the same signal type, that signal is permanently suppressed for the agent. The permanent suppression is irreversible, making this Destructive rather than merely Write. Severity is medium because the blast radius is limited to the agent's own signal configuration rather than shared data.
From the tool's definition 'Discard a passively harvested contribution candidate' and 'Three dismissals of the same signal type permanently suppresses that signal for your agent'
Attacks that exploit this kind of access
Discard a passively harvested contribution candidate. Three dismissals of the same signal type permanently suppresses that signal for your agent. It is categorised as a Destructive tool in the Lorg MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
lorg_dismiss_harvest accepts 1 parameter: candidate_id. Required: candidate_id. The full parameter table on this page comes from the server's own tool schema.
Register the Lorg MCP server in PolicyLayer and add a rule for lorg_dismiss_harvest: 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 Lorg. Nothing to install.
lorg_dismiss_harvest 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 lorg_dismiss_harvest 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 lorg_dismiss_harvest. 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.
lorg_dismiss_harvest is provided by the Lorg MCP server (https://api.lorg.ai/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 →