The Model Context Protocol lets many agent applications discover and call one shared capability. This site starts from one plain function that reads a roof assessment and climbs, one step at a time, to a remote MCP server used by four teams: when a function, an HTTP API or MCP is the right choice, how identity and authorization really work, who may publish and approve a tool, and how a platform team keeps a shared capability safe, observable and governable.
An insurer's assessment service is wanted by intake, underwriting, claims and analytics agents. Giving every agent database credentials is unsafe; wrapping the service in MCP does not make it safe either, because the protocol carries the call, not the permission. MCP engineering decides when a protocol server is worth it, and then puts identity, scoped authorization, audit and ownership around it.
A plain function, function calling, client and server, then MCP: host, client, server, tools, resources and prompts, per the current revision.
Local or remote, the database decision (same-process code, a Java service or an MCP adapter), and when sharing across teams justifies a protocol.
User versus agent identity, OAuth scopes, enterprise-managed authorization, no token passthrough, and the threat model: injection, tool poisoning, confused deputy.
Governance and ownership, the publishing lifecycle, audit, resilience, testing and an enterprise reference architecture.