Many discussions about Model Context Protocol (MCP) focus on an AI assistant calling an API and returning a result. Banking requires more than pass-through connectivity: governance, transparency, auditability, trust and human oversight must be present throughout the analytical lifecycle.
The SAS Viya MCP Server addresses that challenge by exposing SAS data, analytics, models and decisioning capabilities as standardized MCP tools that AI assistants such as Claude Cowork and other MCP-compatible clients can securely consume. Rather than executing the analytical work itself, the AI assistant becomes an orchestration interface, while SAS Viya remains the trusted execution layer behind the workflow.
This post highlights a credit evaluation use case and the architectural components behind it. The centerpiece is a 10-minute demo of SAS Viya MCP Server and Claude Cowork. Watch it now, or keep reading for a closer look at the architecture behind it.
Large language models (LLMs) excel at understanding language and reasoning over information, but they have no inherent awareness of enterprise data, analytical assets or business processes. MCP provides a standardized way for AI assistants to discover and invoke enterprise capabilities.
The SAS Viya MCP Server extends that concept by exposing trusted SAS assets as governed tools. Available as an open-source project on GitHub, the SAS Viya MCP Server currently includes more than 40 capabilities spanning data governance, data access, AutoML, model management, reporting and interaction with deployed models and decisions.
This makes it possible to orchestrate analytical workflows through natural language while execution, governance and lifecycle management remain within SAS Viya. Existing analytical investments including models, decision flows, governance frameworks and domain expertise can be reused rather than recreated inside LLM applications.
In the banking demo, Claude Cowork orchestrates creating a credit classification model designed to predict whether an applicant represents a good or bad credit risk. Using a recently released data set from Santander AI Lab to augment a well-known German credit data set, a natural language request coordinates multiple activities across SAS Viya:
- Data ingestion
- Data profiling and governance review
- Automated machine learning
- Model evaluation and comparison
- Model publication
- Operational scoring
The value is not that an AI assistant can build a model. The value is that the assistant can coordinate a governed analytical workflow while trusted SAS services perform the underlying analytical work. The result is a more efficient path from data to insight without sacrificing transparency or control.
Many agentic AI demonstrations focus on automation. Regulated industries such as banking require more than automation. They need workflows that can be reviewed, explained and controlled.
In this workflow, analytics and model management remain within SAS Viya. Users can examine profiling results, review model pipelines, validate outputs and understand how results were generated rather than relying on a black-box process.
Human approval also remains part of the model life cycle. Models generated through the workflow are not automatically deployed; stakeholders review and approve assets before deployment. That distinction matters in banking and other regulated environments where oversight, validation and approval are mandatory.
Pay attention to several architectural patterns in the demo:
- SAS capabilities are exposed as standardized MCP tools, rather than through custom integrations.
- Analytical execution remains inside SAS Viya while the AI assistant orchestrates activity.
- Governance, auditability and access controls remain enforced through existing SAS capabilities.
- Enterprise platform details and internal SAS endpoints are not exposed directly to the underlying LLM.
- Human approval remains part of the model lifecycle before deployment.
- Existing SAS assets, models and analytical workflows can be reused rather than rebuilt for each AI assistant experience.
These patterns are applicable well beyond credit modeling and can be extended to fraud detection, marketing optimization, customer intelligence, anti-money laundering and other analytics-driven business processes.
If you’re ready to move from concept to hands-on practice, dive into these resources:
1. Free Hands-On Lab: Agentic AI – How To with SAS Viya
Use SAS Agentic AI Accelerator to:
- Register, publish, and deploy proprietary and open source LLMs.
- Build decision workflows that combine LLM judgment with deterministic models.
- Deploy AI-driven decisions into Azure AI Assistants.
- Monitor model cost, performance, and sentiment.
- Gain practical experience with AI governance in a real-world environment.
2. Training: SAS Decisioning Learning Subscription
A new SAS Viya MCP Server chapter will teach you how to:
- Connect Claude Cowork to SAS Viya.
- Connect GitHub Copilot to a governed SAS Viya environment.
- Work within enterprise-grade governance and decisioning frameworks.
