Jaina

What is MCP?

A short primer on the Model Context Protocol and why Jaina uses it.

In one paragraph

The Model Context Protocol (MCP) is a tool-call protocol between an AI client (Claude Desktop, Claude Code, etc.) and an MCP server. The server declares a list of tools with JSON Schema-typed parameters. The client decides when to call them based on the user's conversation. The server executes the tool and returns a result.

Why it exists

Before MCP, every AI integration with a third-party system was bespoke. Each tool had its own protocol, its own auth, its own way of describing inputs and outputs. MCP standardizes the contract so any AI client can talk to any MCP server.

What MCP gives you

  • Tool discovery — the client can ask "what can you do?" and get a typed list.
  • Typed parameters — JSON Schema means the AI knows what shape each call expects.
  • Authenticated sessions — bearer tokens, OAuth, or other mechanisms.
  • Bidirectional communication — long-running operations, streaming, resources.

Why Jaina exposes an MCP server

Because Jaina's content layer should be as available to AI agents as it is to humans (GUI) and apps (REST API). The three-doors principle: same data, three equal access paths.

When you define a schema in Jaina, the MCP server automatically gains tools for that schema:

  • jaina_list_records for that schema
  • jaina_create_record with a typed data payload matching your fields
  • jaina_update_record, jaina_delete_record
  • Custom action invocations if you've defined any

No tool definitions to hand-write. No bespoke integration code. The tools update when the schema updates.

What this enables

  • "Add three new enemies to my game" — Claude makes three valid records with proper field types.
  • "Find blog posts published last month with the 'mcp' tag" — Claude calls jaina_list_records with a filter and shows the results.
  • "Generate a TypeScript model for the Enemy schema" — Claude calls jaina_get_schema_fields and emits the type.

The whole content layer becomes addressable through conversation.

Where to learn more