Add mcp-advanced module: resources, prompts, sampling and elicitation on Spring AI 2.0.2 and MCP Java SDK 2.1.0

An incident-desk MCP server with a fixed resource, two resource templates, a prompt, a tool that borrows the client's model (sampling) and a tool that asks the operator to approve a restart (elicitation). Driven by a plain SDK client in JUnit and by raw curl, so the JSON-RPC for both server-to-client requests is committed. Also captured: a client that declared neither capability (a gated tool degrades, an ungated one returns an isError result), a slow client hitting the server request timeout, and protocol=STATELESS silently dropping every tool that takes McpSyncRequestContext (one WARN line, an empty tools/list). Negotiated protocol version is 2025-11-25; the 2026-07-28 spec is not implemented by SDK 2.1.0. No docs/ folder. Co-Authored-By: Claude Sonnet 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_017ic4b5jAFLJrmUXmbo5EuV
2026-11-10 18:47:09 +00:00
parent 68da642f9a
commit 0006167c24
27 changed files with 1033 additions and 0 deletions
@@ -0,0 +1,13 @@
+# tools/call summarize_incident -> server sends sampling/createMessage to the client
+what the CLIENT received from the server:
+  systemPrompt: You are an SRE. Answer in two sentences, no preamble.
+  messages: 1
+  messages[0].role: USER
+  messages[0] starts with: Summarize this incident log:
+  maxTokens: 120
+  temperature: 0.2
+  includeContext: NONE
+
+tool result returned to the caller:
+Connection pool on payments-api was exhausted by a 14.8s ledger query, so 212 clients got HTTP 503. Fix the query or raise the pool.
+isError: false