Files
spring-ai/mcp-advanced/output/10-wire-sampling.txt
T
asmhatreandClaude Sonnet 5.5 0006167c24 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

57 lines
1.4 KiB
Plaintext

# sampling/createMessage on the wire
## 1. client -> server (POST, answers arrive later on the same session)
tools/call summarize_incident {"incidentId":"INC-1043"}
## 2. server -> client, on the SSE stream of that same POST
{
"jsonrpc": "2.0",
"method": "sampling/createMessage",
"id": "7899c995-7e19-45a9-8b27-a043acabe802-0",
"params": {
"messages": [
{
"role": "user",
"content": {
"type": "text",
"text": "Summarize this incident log:\n11:02:44 search-api WARN index segment merge running\n11:02:51 search-api INFO p99 latency 840ms (SLO 500ms)\n"
}
}
],
"systemPrompt": "You are an SRE. Answer in two sentences, no preamble.",
"includeContext": "none",
"temperature": 0.2,
"maxTokens": 120
}
}
## 3. client -> server, a NEW POST carrying the answer (same id as the server's request)
{
"jsonrpc": "2.0",
"id": "7899c995-7e19-45a9-8b27-a043acabe802-0",
"result": {
"role": "assistant",
"content": {
"type": "text",
"text": "A segment merge pushed p99 to 840ms against a 500ms SLO."
},
"model": "curl-model",
"stopReason": "endTurn"
}
}
## 4. server -> client, the original tools/call finally completes
{
"jsonrpc": "2.0",
"id": 7,
"result": {
"content": [
{
"type": "text",
"text": "A segment merge pushed p99 to 840ms against a 500ms SLO."
}
],
"isError": false
}
}