Presentation: APIs for Agents: Rethinking API Programs in the MCP Era
Morgan Stanley built the API infrastructure for agent-to-agent commerce. Here's how they scaled it without breaking production.
Why it matters
Enterprise agents aren't a prototype problem anymore—they're a platform problem. This is how a major financial institution engineered governance, safety, and scale for multi-agent workflows in production.
The key facts
10 to knowMorgan Stanley integrating Model Context Protocol (MCP) and Agent-to-Agent (A2A) communications
Architecture as Code with CALM for API governance automation
Deployment gates enforcing automated governance for agent workflows
Zero-downtime platform upgrades for agentic systems at scale
Enterprise agents across multiple workflows (implied scale beyond pilot)
Morgan Stanley uses Architecture as Code (CALM) to modernize API program
Integration of Model Context Protocol (MCP) and Agent-to-Agent (A2A) communications
Automated governance enforcement through deployment gates
Zero-downtime platform upgrades for agentic workflows
Focus on safe scaling of enterprise AI and agents
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: Jim Gough and Andreea Niculcea explain how Morgan Stanley uses Architecture as Code with CALM to modernize its API program. They demonstrate integrating Model Context Protocol (MCP) and Agent-to-Agent (A2A) communications, enforcing automated governance through deployment gates, and executing…