evaluate_threshold

Instructions

Implementation Reference

• src/mcp/tools/evaluate-threshold.ts:14-43 (handler)

  The handler function that registers and implements the evaluate_threshold MCP tool. It uses engine.thresholdMonitor.getReading(), engine.healthAssessor.assess(), and engine.thresholdMonitor.getBreakdown() to compute the Storey Threshold and returns escalation rate, status, recommendation, and breakdown.

  export function registerEvaluateThresholdTool(server: McpServer, engine: GovernanceEngine): void {
    server.tool(
      'evaluate_threshold',
      'Compute the Storey Threshold — escalation rate (gates required / total operations). Returns current rate, status, and recommendations. Healthy band 10-18% is a design heuristic, not empirically validated.',
      {},
      { title: 'Evaluate Storey Threshold', readOnlyHint: true, idempotentHint: true, destructiveHint: false, openWorldHint: false },
      async () => {
        const reading = engine.thresholdMonitor.getReading();
        const health = engine.healthAssessor.assess();
        const breakdown = engine.thresholdMonitor.getBreakdown();
  
        // Tool accountability tracking
        engine.telemetryService.emitToolCall('evaluate_threshold', `threshold-${Date.now().toString(36)}`, 'INFORMATIONAL', true);
  
        return {
          content: [{ type: 'text' as const, text: JSON.stringify({
            escalationRate: `${(reading.escalationRate * 100).toFixed(1)}%`,
            healthyBand: '10-18%',
            status: reading.status,
            isHealthy: reading.isHealthy,
            windowSize: reading.windowSize,
            breakdown,
            recommendation: health.recommendation,
            actionRequired: health.actionRequired,
            severity: health.severity,
          }, null, 2) }],
        };
      }
    );
  }

• src/mcp/server.ts:27-93 (registration)

  Import and registration of the evaluate_threshold tool in the MCP server's TOOL_REGISTRY, categorized as 'public' tier visibility.

  import { registerEvaluateThresholdTool } from './tools/evaluate-threshold.js';
  import { registerScoreGovernanceTool } from './tools/score-governance.js';
  import { registerAuditPipelineTool } from './tools/audit-pipeline.js';
  import { registerMonitorAgentsTool } from './tools/monitor-agents.js';
  import { registerMapComplianceTool } from './tools/map-compliance.js';
  import { registerAssessRiskTierTool } from './tools/assess-risk-tier.js';
  import { registerGenerateReportTool } from './tools/generate-report.js';
  import { registerSystemStatusTool } from './tools/system-status.js';
  import { registerApproveGateTool } from './tools/approve-gate.js';
  import { registerAgentRightsTool } from './tools/agent-rights.js';
  import { registerPrecedentTools } from './tools/precedent.js';
  import { registerCitizenshipTools } from './tools/citizenship.js';
  import { registerBranchAuthorityTools } from './tools/branchAuthority.js';
  import { registerColonyTools } from './tools/colony.js';
  import { registerMemoryPackTools } from './tools/memory-packs.js';
  import { registerValueMetricsTools } from './tools/value-metrics.js';
  import { registerSRTTools } from './tools/srt.js';
  import { registerVerifyLedgerTool } from './tools/verify-ledger.js';
  import { registerExportLedgerTool } from './tools/export-ledger.js';
  import { registerRemediationPackTools } from './tools/remediation-packs.js';
  import { registerPhoenixRecoveryTools } from './tools/phoenix-recovery.js';
  import { registerGovernedRetrievalTools } from './tools/governed-retrieval.js';
  import { registerContextAuthorityTool } from './tools/context-authority.js';
  import { registerInstitutionTools } from './tools/institution.js';
  import { registerContextReviveTool } from './tools/context-revive.js';
  import { registerGovernedSamplingTool } from './tools/governed-sampling.js';
  import { registerChainOfReasoningTools } from './tools/chain-of-reasoning.js';
  import { GovernedSampling } from '../core/sampling/index.js';
  
  // Runtime accountability instrumentation — wraps server.tool() registrations
  // so every invocation is bookended with startSession()/endSession().
  import { wrapServerWithRuntimeAccountability } from './runtime-accountability-wrapper.js';
  
  // Import resource handlers
  import { registerResources } from './resources/index.js';
  
  // Import prompt handlers
  import { registerPrompts } from './prompts/index.js';
  
  // ============================================================================
  // Tool Visibility Tiers — Tenant Isolation for External MCP Clients
  // ============================================================================
  //
  // Three tiers control which tools are registered per session:
  //   PUBLIC   — stateless scoring/classification tools, safe for any external client
  //   TENANT   — tools that access data, filtered by tenant ID (professional+ tier)
  //   OPERATOR — internal infrastructure tools (local stdio only, never exposed externally)
  //
  // The Smithery gateway and all HTTP clients get PUBLIC by default.
  // Paying customers (professional/enterprise DB keys) get PUBLIC + TENANT.
  // Local stdio (Claude Code / Claude Desktop) gets all tiers (OPERATOR).
  // ============================================================================
  
  export type ToolVisibility = 'public' | 'tenant' | 'operator';
  
  /**
   * Maps each tool registration function to its visibility tier.
   * Grouped by the tier each set of tools belongs to.
   */
  const TOOL_REGISTRY: Array<{
    tier: ToolVisibility;
    register: (server: McpServer, engine: GovernanceEngine) => void;
    description: string;
  }> = [
    // --- PUBLIC: Stateless governance scoring — no data exposure ---
    { tier: 'public', register: registerClassifyDecisionTool, description: 'classify_decision' },
    { tier: 'public', register: registerEvaluateThresholdTool, description: 'evaluate_threshold' },

• src/core/audit/telemetry.ts:164-164 (schema)

  Accountability profile for evaluate_threshold: toolClass='read', riskTier='low', maiDefault='INFORMATIONAL', no human approval required, governance category.

  { toolName: 'evaluate_threshold',  toolClass: 'read',     riskTier: 'low',      maiDefault: 'INFORMATIONAL',  requiresHumanApproval: false, category: 'governance' },

• src/mcp/prompts/index.ts:45-47 (helper)

  Prompt instructions referencing evaluate_threshold as a tool to use for governance health assessment (4 occurrences across various prompt templates).

    `4. Use evaluate_threshold to check governance health.`,
    `5. Summarize findings with specific recommendations for governance configuration.`,
  ].join('\n'),

• src/onboarding/generate-client-config.ts:207-207 (helper)

  Onboarding documentation listing evaluate_threshold under the Classification category of available tools.

  | Classification | classify_decision, evaluate_threshold, score_governance |