Build a Dart ADK Agent and MCP Server

A developer has released an open-source project that enables Dart developers to build AI agents and Model Context Protocol (MCP) servers without relying on Python or Node.js. The project, adk-hello-world-dart, uses the adk_dart library for the agent and Shelf for an HTTP server that exposes an MCP-compatible greeting tool over Server-Sent Events. The developer notes that the Dart library is not an official ADK, as an official Dart ADK has not been released as of July 2026.

Dart developers do not need a Python or Node.js service just to experiment with agents and Model Context Protocol MCP tools. This project uses adk dart for the agent and shelf for a small HTTP server that exposes an MCP-compatible greeting tool over Server-Sent Events SSE . The complete code is in the adk-hello-world-dart repository https://github.com/xbill9/adk-hello-world-dart . Note- the Dart library is not an official ADK. An official Dart ADK has not been released as of July 2026. This approach provides an alternative to start working with agents in Dart without waiting for an official SDK. The repository has two related examples: bin/main.dart creates an LlmAgent and registers an ADK FunctionTool . bin/server.dart starts a Shelf server with an SSE endpoint and a JSON-RPC message endpoint.The server implements the MCP methods needed by this demo: initialize , notifications/initialized , ping , tools/list , and tools/call . The transport and JSON-RPC routing are deliberately small and live in SessionService ; they are not a general-purpose MCP server implementation. php flowchart LR Client MCP client -- |GET /sse| Server Shelf server Server -- |endpoint event| Client Client -- |POST /messages?sessionId=...| Server Server -- Session SessionService Session -- Tool greet tool CLI Dart CLI -- Agent ADK LlmAgent Agent -- ADKTool ADK FunctionTool The current project targets Dart 3.5 or later and uses these package versions: environment: sdk: ^3.5.0 dependencies: adk dart: ^2026.7.24 adk mcp: ^2026.7.24 logging: ^1.3.0 shelf: ^1.4.1 shelf router: ^1.1.4 uuid: ^4.5.1 Install them with: dart pub get adk dart is used directly by the sample agent. The repository also tracks adk mcp , while the current server keeps its MCP transport explicit in SessionService so the protocol flow is easy to inspect. The project keeps the greeting logic separate from its ADK and MCP wrappers: class Tools { static String formatGreeting String name { return 'Hello, $name '; } static final FunctionTool greetFunctionTool = FunctionTool name: Config.toolGreet, description: 'Get a greeting from a local HTTPS server.', func: {String? param} { final name = param ?? 'World'; return formatGreeting name ; }, ; } Tools also exposes an MCP tool definition with a JSON Schema input named param . Keeping formatGreeting as a plain Dart function makes the domain behavior easy to unit test. AdkGreetingAgent attaches the function tool to an LlmAgent : class AdkGreetingAgent { static LlmAgent createAgent { return LlmAgent name: 'GreetingAgent', description: 'An AI Agent built with adk dart that provides greetings.', instruction: 'You are a friendly greeting assistant. ' 'Use the greet tool to provide personalized greetings.', tools: Tools.greetFunctionTool , ; } } Run the CLI example to confirm that the agent and tool can be created: dart run bin/main.dart This command initializes the agent and prints a sample tool result. It does not call a hosted model. The Shelf server registers four routes: js router.get '/', request = Response.ok 'ADK & MCP Dart Server Running' ; router.get '/health', request = Response.ok 'OK' ; router.get Config.sseEndpoint, sessionService.handleSseSession ; router.post Config.messagesEndpoint, sessionService.handlePostMessage ; When a client opens GET /sse , SessionService creates an in-memory session and sends an endpoint event containing a URL such as: /messages?sessionId=7c6d... The client posts JSON-RPC requests to that URL. Responses arrive as message events on the original SSE connection. Start the server with: dart run bin/server.dart It listens on port 8080 by default. Set the PORT environment variable to use another port. For an MCP client that supports remote SSE servers, point it at: http://localhost:8080/sse A typical client configuration looks like this: { "mcpServers": { "dart-greeting-server": { "url": "http://localhost:8080/sse" } } } Configuration keys differ between MCP clients, so check the documentation for the client you use. Once connected, call the greet tool with: { "param": "Dart developer" } The result is Hello, Dart developer . The repository includes unit tests for the greeting behavior and endpoint tests for the Shelf server: dart test dart analyze You can run the complete build, analysis, and test sequence with: make check The included multi-stage Dockerfile compiles the server to a native executable and copies it into a small scratch image: docker build -t adk-hello-world-dart . docker run --rm -p 8080:8080 adk-hello-world-dart Check the running container at http://localhost:8080/health . cloudbuild.yaml builds the image, pushes it to Container Registry, and deploys the service in us-central1 : make deploy The deployment allows unauthenticated access and sets --max-instances 1 . That instance limit matters here. Active SSE transports are stored in a process-local map, so a POST request routed to another instance would not find its session. A production service should move session state to shared storage or use a transport and deployment design that does not depend on process-local routing. Authentication, origin restrictions, request validation, timeouts, and rate limiting would also need attention before exposing the service publicly. This sample is intentionally narrow: one agent, one deterministic tool, and enough MCP handling to show the request flow. Useful next steps include replacing the greeting with real domain logic, using adk mcp transport primitives as the Dart package evolves, adding model configuration to execute the agent, and moving session state out of memory before scaling the service. Resources: