When the user asks about agent-to-agent handoff, conversation delegation between agents, signed handoff certificates, or preventing scope creep across trust boundaries, use agent-handoff-certified-mcp tools.
When the user asks about agent IAM, per-agent-pair policies, agent authorization rules, multi-tenant agent governance, or "agent A may only talk to agent B if X", use agent-policy-enforcement-mcp tools.
When the user asks about agriculture robotics, use agriculture-robotics-mcp tools: robotsafetycheck, sprayplancalculator, harvestoptimization, droneflightplan, soilanalysis.
When the user asks about AI Bill of Materials, AI-BOM, supply chain transparency, model dependencies, training data provenance, or model card generation, use ai-bom-mcp tools.
When the user asks about AI incident reporting, serious incident classification, EU AI Act Article 73, OECD AI Incident Monitor (AIM), or multi-regime incident routing, use ai-incident-reporting-mcp tools.
When the user asks about api docs generator, use api-docs-generator-ai-mcp tools: generateendpoint, generateschema, generatefullspec, addauthtospec, validatespec.
When the user asks about AI bias, fairness assessment, demographic parity, disparate impact, protected attributes, or model fairness metrics, use bias-detection-mcp tools.
When the user asks about blockchain, use blockchain-ai-mcp tools: walletanalyzer, transactiontracer, smartcontractauditor, gasestimator, tokenmetadata.
When the user asks about canada aida, use canada-aida-ai-mcp tools: classifyaisystem, impactassessment, compliancecheck, crosswalktoeuaiact, generatedocumentation.
When the user asks about churn predictor, use churn-predictor-ai-mcp tools: predictchurn, batchpredictchurn, getcustomerrisk, trackcustomer, updatecustomersignals.