MCP in action ParisJUG

Transcript

1. MCP en action: Connecter les IA aux systèmes d’entreprise Zineb Bendhiba, Principal Software Engineer, Red Hat
3. Model Context Protocol
4. Input LLM Output Prompt
5. Tools / functions
6. Model Context Protocol (MCP)
7. demo
8. MCP - more details
9. Model Context Protocol (MCP) A new protocol - A standard for connecting AI agents to systems - Pushed by Anthropic (Claude) USB for AI integrations
10. Capabilities Tools - The client can invoke “tool” and get the response - Close to function calling, but the invocation is requested by the client - Can be anything: database, remote service… Resources - Expose data - URL -> Content Prompts - Pre-written prompt template - Allows executing specific prompt
11. Transport JSON-RPC 2.0 - Everything is JSON - Request / Response and Notifications - Possible multiplexing Transports - stdio -> The client instantiates the server, sends the requests on stdio and gets the response from the same channel - Server-Sent Event (SSE) -> The client sends a POST request to the server, the response is an SSE (chunked response) - Streamable HTTP ->
12. Create my MCP server
13. Quarkus MCP server extensions 2 extensions - SSE (SSE) -> quarkus-mcp-server-sse - stdio -> quarkus-mcp-server-stdio
14. Quarkus MCP server extensions @Inject CodeService codeService; @Tool(description = "Converts the string value to lower case" ) String toLowerCase(String value) { return value.toLowerCase(); } @Prompt(name = "code_assist") PromptMessage codeAssist(@PromptArg(name = "lang") String language) { return PromptMessage.withUserRole(new TextContent(codeService.assist(language))); } @Resource(uri = "file:///project/alpha" ) BlobResourceContents alpha(RequestUri uri) throws IOException{ return BlobResourceContents.create(uri.value(), Files.readAllBytes(Path.of("alpha.txt"))); } MCP Tool MCP Prompt MCP Resource
15. Show me some <code>
16. Create an AI infused-app with MCP server
17. Model and Model Serving Model Model Serving Model Serving - Run the model - CPU / GPU - Expose an API Input - Prompt (text) - Instructions to give to the model - Taming a model is hard GPUs Input (Prompt) Output
18. Application Model AI-infused application |ˌeɪˌaɪ ˈɪnˌfjuːzd ˌæplɪˈkeɪʃən| noun (Plural AI-Infused applications) A software program enhanced with artificial intelligence capabilities, utilizing AI models to implement intelligent features and functionalities. Model Serving
19. So… basically, you just call a REST API, right ? [Spoiler Alert: No]
20. Model <= HTTP Client <= Application HTTP Client Leaking HTTP stuff or abstractions - Often leak HTTP details - Error code, connection pooling - Requires implementing memory and token counting logic Application
21. The need for abstractions: Memory Application LLM (stateless) Context / Memory
22. LangChain (Python, JS) LangChain Chains Agents Prompts Vector Stores Document Loaders Models
23. LangChain4j LangChain4j Chains Agents Prompts Document Loaders Vector Stores Models https://github.com/langchain4j/langchain4j
24. Is Langchain4j enough?
25. LangChain / LangChain4j / Quarkus LangChain4j LangChain LangChain4j Quarkus LangChain4j Inspired By Uses and extends Framework Clean separation, Managed interactions Integration Application
26. Quarkus LangChain4j https://docs.quarkiverse.io/quarkus-langchain4j LangChain4j Quarkus LangChain4j Application LLMs Vector stores Embedding Models - Declarative clients - CDI integration - Observability (Otel, Prometheus) - Auditing - Resilience - Guardrails - RAG building blocks - Agentic architecture - Testability (unit, IT, evaluation) - Developer Joy
27. Show me some <code>
28. MCP client
29. Agent and MCP servers MCP servers offer new tools and resources that the model can call: Prompt (Context) Extend the context with MCP tools descriptions Invoke the model The model invoke a tool invocation (name + parameters) The tool is invoked via JSON-RPC and the result sent to the model The model computes the response using the tool result Response
30. Quarkus Langchain4j MCP client extension quarkus.langchain4j.mcp.filesystem. transport-type =stdio quarkus.langchain4j.mcp.filesystem. command=npx,-y,@modelcontextprotocol/s erver-filesystem,/my-system-path/location quarkus.langchain4j.mcp.wanaku. transport-type =http quarkus.langchain4j.mcp.wanaku. url=http://my-url/mcp/sse/ stdio SSE
31. Show me some <code>
32. Observations
33. My obsertavtions - Most of servers are stdio - Entreprise vs Local - Lack of documentation for SSE - Security - Authentication - Wanaku experience : limitation in the number of tools - MCP and Agentic -> emerging A2A - Not the only protocol (ACP …)
34. Thank you
35. Links - https://docs.quarkiverse.io/quarkus-langchain4j/dev/index.html - https://quarkus.io/blog/mcp-server/ - https://www.wanaku.ai/ - https://quarkus.io/blog/secure-mcp-sse-server/ - https://www.anthropic.com/news/model-context-protocol - Quarkus Langchain4j à Devoxx France