Building an AI Chat Agent with MCP, Spring AI

A developer built an AI chat agent using Model Context Protocol (MCP), Spring AI, and Google Gemini to answer weather questions with real tool integration. The system includes a Spring Boot MCP server exposing weather and geocoding tools, and an AI agent that uses Gemini to decide when to call these tools, preventing hallucination. The project demonstrates a scalable architecture for production AI assistants.

Model Context Protocol MCP is an open standard for connecting AI apps to tools and data sources. A useful way to think about it is as a USB-C port for AI: one standard interface that lets different models plug into different capabilities without custom glue code for every integration. In this project, we combine MCP, Spring AI, and Google Gemini to build a chat app that can answer weather questions using real tools instead of hallucinating. The system has three parts: The result is a small but realistic architecture you can extend into a production assistant. User Browser:3000 | POST /api/chat v AI Agent Spring:7171 -- MCP / Streamable HTTP -- MCP Server Spring:7170 | | | Google Gemini | Bright Sky API weather | | OpenStreetMap Nominatim geocoding v v Chat response Tool execution The full source code is available on GitHub https://github.com/ykpraveen/mcp-spring-sample . The tool server is a Spring Boot application that exposes MCP tools through Spring AI's annotation scanner. It runs on port 7170 and uses Streamable HTTP for transport. <dependency <groupId org.springframework.ai</groupId <artifactId spring-ai-starter-mcp-server-webmvc</artifactId </dependency <dependency <groupId org.springframework.boot</groupId <artifactId spring-boot-starter-web</artifactId </dependency With Spring AI, a tool is just a Spring bean method annotated with @McpTool : @Component public class WeatherTool { private final WeatherToolService weatherToolService; public WeatherTool WeatherToolService weatherToolService { this.weatherToolService = weatherToolService; } @McpTool name = "get current weather", description = "Get current weather by dwd station id or by lat/lon" public Map<String, Object getCurrentWeather @McpToolParam description = "DWD station ID", required = false String dwd station id, @McpToolParam description = "Latitude", required = false Double lat, @McpToolParam description = "Longitude", required = false Double lon { return weatherToolService.getWeather dwd station id, lat, lon ; } } Spring turns that method into an MCP tool definition and publishes the parameter metadata as part of the schema. That means the model can discover the tool, understand its inputs, and decide when to call it. The project also includes a geocoding tool that resolves city names to coordinates: @McpTool name = "geocode city", description = "Convert a city name to latitude and longitude using OpenStreetMap Nominatim" public Map<String, Object geocodeCity @McpToolParam description = "City name e.g., 'Berlin', 'New York' ", required = true String cityName { ... } The tools delegate the real work to services that handle validation, caching, and external API calls: @Service public class WeatherToolService { public Map<String, Object getWeather String dwdStationId, Double lat, Double lon { // Validate the request // Check the cache // Call Bright Sky if needed // Return a structured response } } The key design choices are straightforward: success , error code , and error message server: port: 7170 spring: ai: mcp: server: name: spring-sample-mcp-server version: 1.0.0 protocol: STREAMABLE type: SYNC annotation-scanner: enabled: true mcp: security: api-key: ${MCP API KEY:} The STREAMABLE protocol gives the agent a lightweight MCP transport, and the shared API key keeps the demo simple without adding full auth infrastructure. The MCP server and agent share an MCP API KEY . The agent adds it automatically as an X-API-Key header, and the server validates it on inbound MCP requests. That is enough for local development and a sample project. For anything public-facing, move to Spring Security, OAuth2 or JWT, rate limiting, and a gateway in front of the MCP endpoint. The agent is responsible for deciding when to use tools, calling Gemini, and keeping the conversation stateful. <dependency <groupId org.springframework.ai</groupId <artifactId spring-ai-starter-model-google-genai</artifactId </dependency <dependency <groupId org.springframework.ai</groupId <artifactId spring-ai-starter-mcp-client</artifactId </dependency <dependency <groupId org.springframework.boot</groupId <artifactId spring-boot-starter-web</artifactId </dependency The agent injects the shared API key through a custom HTTP request customizer: @Configuration public class AgentConfiguration { @Bean McpClientCustomizer<HttpClientStreamableHttpTransport.Builder streamableHttpTransportCustomizer AgentProperties properties { McpSyncHttpClientRequestCustomizer requestCustomizer = builder, method, uri, body, context - { if StringUtils.hasText properties.getMcpApiKey { builder.header "X-API-Key", properties.getMcpApiKey ; } }; return name, builder - builder.httpRequestCustomizer requestCustomizer ; } } The agent keeps a small in-memory conversation history, checks whether the user message looks like a tool request, and then routes the prompt through either a plain Gemini client or a tool-enabled client. public String reply String sessionId, String userMessage { List<ConversationTurn history = memoryStore.history sessionId ; String prompt = buildPrompt history, userMessage ; boolean toolRequest = shouldUseTools userMessage ; ChatClient client = toolRequest ? toolEnabledClient : plainChatClient; String answer = invokeModel client, prompt ; memoryStore.appendTurn sessionId, userMessage, answer ; return answer; } The lazy initialization is deliberate: the agent can start even if the MCP server is down, and it only initializes MCP clients when a tool request actually arrives. The tool trigger is intentionally simple: private static boolean shouldUseTools String userMessage { String normalized = userMessage.toLowerCase Locale.ROOT ; for String keyword : TOOL KEYWORDS { if normalized.contains keyword { return true; } } return false; } That heuristic is enough for a demo and easy to explain. In a larger system, you could replace it with a router model or intent classifier. The model call runs on a virtual thread with a configurable timeout so the request does not hang forever if Gemini is slow or unreachable: js private String invokeModel ChatClient client, String prompt { var executor = Executors.newVirtualThreadPerTaskExecutor ; try { var future = executor.submit - client.prompt .user prompt .call .content ; return future.get timeoutSeconds, TimeUnit.SECONDS ; } catch TimeoutException ex { throw new ResponseStatusException HttpStatus.GATEWAY TIMEOUT, ... ; } finally { executor.shutdownNow ; } } Conversation history lives in an in-memory LRU store with a small per-session turn window. That keeps follow-up questions like "What about tomorrow?" grounded in the earlier exchange without introducing a database too early. The agent configuration sets the model to gemini-3.5-flash , the memory limit to 20 turns per session, and the session cap to 500. The frontend is a Vite app with a simple chat window, minimal state, and no component library. const messages, setMessages = useState ; const loading, setLoading = useState false ; const sendMessage = async text = { setMessages prev = ...prev, { role: 'user', content: text } ; setLoading true ; const response = await fetch '/api/chat', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify { sessionId, message: text } } ; const data = await response.json ; setMessages prev = ...prev, { role: 'assistant', content: data.reply || 'No response' } ; setLoading false ; }; The Vite dev server proxies /api/ to the agent: proxy: { '/api': { target: 'http://localhost:7171', changeOrigin: true, rewrite: path = path.replace /^\/api/, '' } } The UI is intentionally plain: a purple gradient, responsive layout, and a smooth message list are enough to make the app feel complete without distracting from the architecture. export GEMINI API KEY=your gemini api key export MCP API KEY=a shared secret cd mcp-server-spring mvn spring-boot:run cd mcp-spring-agent mvn spring-boot:run cd mcp-ui npm install npm run dev If the user asks, "What's the weather in Berlin?" the flow looks like this: geocode city "Berlin" to get coordinates get current weather lat=52.52, lon=13.41 MCP separates the model from the tools. The agent knows what tools exist and how to call them, but not how those tools are implemented. That makes the system easier to evolve. The same server can serve different models. Gemini is just the model in this demo. The MCP server itself can work with any compatible client. Lazy initialization keeps the app resilient. The agent can boot even if the MCP server is temporarily unavailable, and tool support only activates when it is actually needed. This sample is a solid starting point. Natural next steps include: Have you built anything with MCP and Spring AI? I'd love to hear how you approached it.