Building an MCP Tool with Spring Boot AI
How I turned Apache Kafka into a set of tools an AI client can call — using Spring AI's MCP server, a handful of @Tool methods, and one ugly-but-necessary servlet filter.
Topic
The Model Context Protocol, hands on
Building MCP servers and pointing agents at real systems — Spring Boot tools, an email inbox, a JVM agent framework.
Field notes: running my Fastmail inbox over MCP
Field notes from wiring Fastmail's MCP server into an AI client and pointing it at my real inbox — the search syntax worth memorising, plus the two gotchas (deferred schemas, and stage-vs-commit on calendar events) that cost me a few minutes.
Also relevant
Posts that touch this subject but live under another topic.
Codex Meets IntelliJ's Debugger: MCP on a Tiny Play App
I connected Codex to IntelliJ's MCP server, then used a one-route Play 3 app to verify the connection with a real breakpoint and a live variable. The exercise also exposed Play's sbt layout and what Action[AnyContent] means.
Security and privacy, in practice
I didn't need an MCP gateway, I needed a smaller credential
I put an MCP server on the public internet so an AI client could file todos onto my private kanban board. The interesting part wasn't the protocol — it was making the dangerous call unrepresentable.
Building agents on the JVM with Embabel · Part 6
The Silent No-Op: Exposing Embabel Agents Over MCP
Turning my JVM agents into MCP tools took one dependency and one annotation. It also took three silent failures -- a starter that suppresses the web server, a shell that eats your CLI flags, and an annotation default that publishes exactly zero tools without telling you.