MCP (Model Context Protocol)
MCP (Model Context Protocol) is an open standard for connecting AI agents to tools and data sources through declared, typed interfaces. Each MCP server exposes capabilities with input and output schemas, so agents call business systems through governed contracts instead of bespoke, per-integration glue code.
In NeoXam Agents
Every tool an agent can call is an MCP server (Streamable HTTP), organized in three namespaces: platform.* for NeoXam product data and actions, agent-specific.* for an agent's own tools, and external.* for a curated, security-reviewed registry of third-party integrations — arbitrary MCP URLs are rejected.
Related terms
See it at work
Reconciliation break investigation
Shipped — V0 pilotOne click on a break: the agent investigates match history and pricing, then returns root cause, evidence and a recommended action — fully traced.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform