MCP (Model Context Protocol)
The m8ty server exposes all its APIs as MCP tools, enabling AI models and agents to discover and interact with the backend through a standardized protocol.
What is MCP?
The Model Context Protocol is a standardized protocol that enables AI models to interact with external tools and resources in a structured way. It acts as a bridge between AI models and the real world — allowing them to access databases, APIs, file systems, and other services through a consistent interface.
MCP servers provide three main types of capabilities:
Resources — File-like data that can be read by clients (API responses, file contents)
Tools — Functions that can be called by the LLM (with user approval)
Prompts — Pre-written templates that help users accomplish specific tasks
Spring AI MCP Integration
The m8ty server uses Spring AI MCP to expose all APIs as MCP tools. This means any MCP-compatible AI client can discover and call m8ty APIs without custom integration code.
Spring AI provides:
MCP Server Boot Starters — Auto-configuration for exposing Spring services as MCP tools
Multiple transport mechanisms — STDIO, SSE, and Streamable-HTTP
MCP Java Annotations — Declarative way to mark methods as MCP tools
Architecture
How it works
The AI client connects to the m8ty MCP server endpoint
It discovers available tools via the MCP catalog
The LLM selects and calls tools based on user intent
The m8ty server executes the API call and returns structured results
Available MCP Tools
All m8ty REST API endpoints are exposed as MCP tools, including:
Account information (list, search, balance trends)
Transactions (search, details, forecast)
Payments (create, validate, approve)
Cards management
Portfolio and custody accounts
Securities and brokerage orders
Bank documents and secure mails
Feature flags and customer data
Client Integration
Any MCP-compatible client can connect to the m8ty server. The m8ty_client_mcprag Dart package provides additional capabilities for semantic tool search via embeddings — allowing clients to find the most relevant API tool by describing what they need in natural language.