Tool Defense - Stackone

Defender scans tool call responses for prompt injection before they reach your LLM. It runs server-side on every RPC call, so it protects any agent — MCP, the Agent SDK, or a direct API call — regardless of language. Project-wide settings live in the dashboard — see Defender for the concept and configuration. This page covers per-toolset overrides in the SDK.

Per-toolset SDK configuration

Per-toolset SDK configuration is currently available only in the TypeScript SDK (@stackone/ai). Python agents still get Defender via the dashboard setting — it runs server-side on every call.

Override the dashboard setting for a specific toolset with the defender option on StackOneToolSet. It accepts four shapes:

`defender` value	Behavior
omitted (default)	Project dashboard setting controls
`{ useProjectSettings: true }`	Same as omitting — explicit and self-documenting
`{ enabled, blockHighRisk, useTier1Classification, useTier2Classification }`	SDK-level config overrides the dashboard
`null`	Forcibly disables Defender for this toolset

import { DEFAULT_DEFENDER_CONFIG, StackOneToolSet } from '@stackone/ai';

// Scan with safe defaults, but block on HIGH or CRITICAL risk
const toolset = new StackOneToolSet({
  defender: { ...DEFAULT_DEFENDER_CONFIG, blockHighRisk: true },
});

toolset.defenderMode; // 'project' | 'disabled' | 'explicit'

When Defender runs, the RPC response includes a defenderMetadata sibling next to data with the risk level, sanitized fields, and detections. See the full TypeScript reference for every config field, the resolved-mode getter, and the override warnings.

Tool Discovery Actions Metadata

​Per-toolset SDK configuration

Per-toolset SDK configuration