Ready Layer One: Intro to the Model Context Protocol
- 1. Intro to the Model Context Protocol READY LAYER ONE MATT MCKENNA #DCNY25 Matt McKenna #dcny25
- 3. WHOLIKESIT?
- 4. WHATWE’LLCOVERTODAY High level view of LLMs and AI Agents What is the Model Context Protocol Android Device control with AI
- 5. TAKEAWAYS Demystify the Model Context Protocol Enable you all to build your own MCP Servers!
- 7. - Sequence prediction at a massive scale WHATISALARGELANGUAGEMODEL(LLM)
- 8. - Sequence prediction at a massive scale - Trained on broad data, fi ne tuned on task speci fi c patterns WHATISALARGELANGUAGEMODEL(LLM)
- 9. - Sequence prediction at a massive scale - Trained on broad data, fi ne tuned on task speci fi c patterns - Interfaces WHATISALARGELANGUAGEMODEL(LLM)
- 10. - Sequence prediction at a massive scale - Trained on broad data, fi ne tuned on task speci fi c patterns - Interfaces - Chat - Code Completion - APIs WHATISALARGELANGUAGEMODEL(LLM)
- 12. - You give the model some text (this is a prompt) HOWDOESANLLMWORK?
- 13. - You give the model some text (this is a prompt) - It tries to predict what comes next a piece at a time HOWDOESANLLMWORK?
- 14. - You give the model some text (this is a prompt) - It tries to predict what comes next a piece at a time - It doesn’t “think” or “know”, but follows patterns HOWDOESANLLMWORK?
- 16. The android developer predict next
- 17. The android developer predict next invalidates
- 18. The android developer predict next invalidates
- 19. The android developer predict next invalidates caches
- 20. The android developer predict next caches invalidates
- 21. The android developer predict next caches invalidates and
- 22. The android developer predict next caches and invalidates
- 23. The android developer predict next restarts caches and invalidates
- 24. The android developer predict next invalidates caches and restarts
- 25. LLMSINACTION
- 26. - Let’s do something with the Android Debug Bridge! (ADB) LLMSINACTION
- 27. - Let’s do something with the Android Debug Bridge! (ADB) - Hey can you write some adb commands for me to launch the Bluesky android app and input text saying “hey from droidcon new york!” and then post it? LLMSINACTION
- 40. IS GREAT THIS
- 43. ENTERAIAGENTS
- 44. WHATISANAIAGENT? A system that uses a language model to complete tasks autonomously or semi-autonomously
- 45. WHATISANAIAGENT?
- 46. - A language model WHATISANAIAGENT?
- 47. - A language model - Tools it can call WHATISANAIAGENT?
- 48. - A language model - Tools it can call - A planner to decide on and sequence actions WHATISANAIAGENT?
- 60. CODENAMEGOOSE
- 61. CLAUDEDESKTOP
- 64. - Tools are the capabilities of the agent AIAGENTSNEEDTOOLS
- 65. - Tools are the capabilities of the agent - Structured input / output AIAGENTSNEEDTOOLS
- 66. - Tools are the capabilities of the agent - Structured input / output - Need to describe - What’s available - When to use - How to use AIAGENTSNEEDTOOLS
- 70. - A JSON based protocol for tool description and invocation THEMODELCONTEXTPROTOCOL
- 71. - A JSON based protocol for tool description and invocation - Share contextual information with LLMs THEMODELCONTEXTPROTOCOL
- 72. - A JSON based protocol for tool description and invocation - Share contextual information with LLMs - Expose tools and capabilities THEMODELCONTEXTPROTOCOL
- 73. - A JSON based protocol for tool description and invocation - Share contextual information with LLMs - Expose tools and capabilities - Build composable integrations and work fl ows THEMODELCONTEXTPROTOCOL
- 74. - A JSON based protocol for tool description and invocation - Share contextual information with LLMs - Expose tools and capabilities - Build composable integrations and work fl ows - Enables tools to describe themselves THEMODELCONTEXTPROTOCOL
- 75. - A JSON based protocol for tool description and invocation - Share contextual information with LLMs - Expose tools and capabilities - Build composable integrations and work fl ows - Enables tools to describe themselves THEMODELCONTEXTPROTOCOL
- 76. MCPFEATURES
- 77. - Resources - File-like data that can be read by clients MCPFEATURES
- 78. - Resources - File-like data that can be read by clients - Prompts - Pre-written templates that help Users accomplish speci fi c tasks MCPFEATURES
- 79. - Resources - File-like data that can be read by clients - Prompts - Pre-written templates that help Users accomplish speci fi c tasks - Tools - Functions that can be called by the LLM MCPFEATURES
- 80. MCPSERVERS
- 81. - Easy to build! MCPSERVERS
- 82. - Easy to build! - Expose Resource, Tools, and Prompts via primitives MCPSERVERS
- 83. - Easy to build! - Expose Resource, Tools, and Prompts via primitives - Can work with local processes and/or remote services MCPSERVERS
- 84. ARCHITECTURE AI AGENT / HOST ADB Weather Calendar Remote Data Source Local Data Source Local Data Source
- 85. ARCHITECTURE AI AGENT / HOST ADB MCP Weather MCP Calendar MCP Remote Data Source Local Data Source Local Data Source Mode l Cont ext Proto col
- 86. LET’SBUILD!
- 87. ADB
- 88. ADB Kotlin
- 89. fun adb(vararg args: String): String { }
- 90. fun adb(vararg args: String): String { val command = listOf("adb") + args }
- 91. fun adb(vararg args: String): String { val command = listOf("adb") + args val process = Runtime.getRuntime().exec(command.toTypedArray()) }
- 92. fun adb(vararg args: String): String { val command = listOf("adb") + args val process = Runtime.getRuntime().exec(command.toTypedArray()) return process.inputStream.bu ff eredReader().readText() }
- 93. ADB Kotlin
- 94. ADB Kotlin MCP
- 97. SERVERSETUP
- 98. fun main(args: Array<String>) { val command = args. fi rstOrNull() ?: "--sse-server-ktor" val port = args.getOrNull(1)?.toIntOrNull() ?: 3001 when (command) { "--stdio" -> runMcpServerUsingStdio() "--sse-server-ktor" -> runSseMcpServerUsingKtorPlugin(port) "--sse-server" -> runSseMcpServerWithPlainCon fi guration(port) else -> { System.err.println("Unknown command: $command") } } }
- 99. fun runSseMcpServerUsingKtorPlugin(port: Int): Unit = runBlocking { println("Starting sse server on port $port") println("Use inspector to connect to the http://localhost:$port/sse") embeddedServer(CIO, host = "0.0.0.0", port = port) { MCP { return@MCP con fi gureServer() } }.start(wait = true) }
- 100. fun con fi gureServer(): Server { val def = CompletableDeferred<Unit>() val server = Server( Implementation( name = "mcp-server-android", version = "0.1.0" ), ServerOptions( capabilities = ServerCapabilities( prompts = ServerCapabilities.Prompts(listChanged = true), resources = ServerCapabilities.Resources(subscribe = true, listChanged = true), tools = ServerCapabilities.Tools(listChanged = true), ) ), onCloseCallback = { def.complete(Unit) } ) //...
- 101. fun con fi gureServer(): Server { //... // Create AdbManager instance val deviceManager = AdbManager() //...
- 102. fun con fi gureServer(): Server { //... // Create AdbManager instance val deviceManager = AdbManager() // Create AndroidToolsRegistry instance and register all tools val toolsRegistry = AndroidToolsRegistry(deviceManager) toolsRegistry.registerTools(server) //...
- 103. fun con fi gureServer(): Server { //... // Add Android device control prompt server.addPrompt( name = "Android Device Control", description = "Control and interact with Android devices through MCP.", arguments = listOf() ) { _ -> // prompt of all tools } return server }
- 104. LETSCODE!
- 106. - Start with work fl ows, not raw endpoints DESIGNTOOLSFROMWORKFLOWS
- 107. - Start with work fl ows, not raw endpoints - Combine steps into a single high level Tool DESIGNTOOLSFROMWORKFLOWS
- 108. - Tool names and params ARE prompts PROMPTFRIENDLYTOOLDESIGN
- 109. - Tool names and params ARE prompts - Better Tool descriptions mean better tool use PROMPTFRIENDLYTOOLDESIGN
- 110. - LLMs context is limited PROTECTTHECONTEXTWINDOW
- 111. - LLMs context is limited - Running out of context window is costly PROTECTTHECONTEXTWINDOW
- 112. - LLMs context is limited - Running out of context window is costly - MCPs can help PROTECTTHECONTEXTWINDOW
- 113. MORERESOURCES
- 114. - Join the community on Bluesky BLUESKY go.bsky.app/Etd57t6
- 115. - Kotlin Multiplatform implementation of MCP MCPKOTLINSDK MODEL CONTEXT PROTOCOL github.com/modelcontextprotocol/kotlin-sdk
- 116. - A local, open source AI agent, automating engineering tasks seamlessly. GOOSE AI AGENT BY BLOCK block.github.io/goose/
- 117. - Best practices and learnings for designing MCP Servers DESIGNINGMCPSERVERS BLOCK’S PLAYBOOK FOR engineering.block.xyz/blog/blocks-playbook-for-designing-mcp-servers
- 119. - Enable Android apps to provide MCP server access to AI tools in development environments ANDROID-MCP-SDK JASON PEARSON’S github.com/kaeawc/android-mcp-sdk
- 120. - Introducing Trailblaze, a natural language AI driven test framework. AIMOBILETESTING - BLAZINGTHETRAILATBLOCK SAM EDWARDS + BRIAN GARDNER STAGE 2 Catch the VOD
- 121. THANKYOU
- 122. Q/A