McpToolset hangs silently for ~5 minutes per retry (3 retries) when stdio command is an npm shim ("npx") on Windows
Maintainer antworten meist innerhalb von 1 Tag
Bewertung
Dieses Issue wurde noch nicht bewertet.
Beschreibung
Description
The examples/mcpfilesystem sample — and any McpToolset built with
command("npx") — appears to hang indefinitely on Windows. No error is
printed and no node.exe process is ever spawned; the caller just blocks
inside McpToolset.getTools().
After digging into it, the "hang" is actually a very slow failure loop:
each initialization attempt waits out the full default
initializationTimeout (5 minutes), and the sync retry logic re-runs the
same doomed initialization, so the program stays silent for a measured
900 seconds (~15 minutes: 3 attempts x 5-minute timeout) before a
McpToolLoadingException (wrapped
Client failed to initialize by explicit API call) finally surfaces —
and even that is invisible unless an SLF4J provider is on the classpath,
which the samples don't include by default.
Environment
- OS: Windows 11 Home (10.0.26200)
- JDK: Oracle 21.0.5
- google-adk: 1.13.0
- Maven: 3.9.8
- Node.js: 24.15.0 (npx 11.12.1, standard npm-for-Windows install with
npx.cmdshim)
Root cause
On Windows, npm installs command shims as batch scripts (npx.cmd), not
executables. Java's ProcessBuilder cannot execute a bare npx command
(it is not a PE executable and is not resolved through PATHEXT), so the
stdio subprocess never starts.
A plain new ProcessBuilder("npx", "-v").start() on the same machine
fails immediately with CreateProcess error=2, which confirms the
JVM/OS-level cause. Inside ADK, however, the failure is masked by:
McpSessionManager.initializeSession(...)defaults the
initializationTimeoutto 5 minutes
(core/src/main/java/com/google/adk/tools/mcp/McpSessionManager.java,
theDuration.ofMinutes(5)fallback), soclient.initialize()waits
for a response from a process that never started.- The sync
McpToolset.getTools()retry logic (MAX_RETRIES = 3,
100 ms delay) then re-runs the same doomed initialization. - Without an SLF4J provider (the default for the samples), even the
retry ERROR logs are swallowed, leaving zero output on the console.
Observed log once an SLF4J provider is added (full run, timestamps from
the measured repro):
ERROR com.google.adk.tools.mcp.McpToolset - Unexpected error during tool loading, retry attempt 1
java.lang.RuntimeException: Client failed to initialize by explicit API call
at io.modelcontextprotocol.client.LifecycleInitializer...
ERROR ... retry attempt 2
ERROR ... retry attempt 3
ERROR com.google.adk.tools.mcp.McpToolset - Failed to load tools after multiple retries due to unexpected error.
com.google.adk.tools.mcp.McpToolsetException$McpToolLoadingException
(total elapsed: 900,857 ms)
Minimal reproduction (public API only)
StdioServerParameters params = StdioServerParameters.builder()
.command("npx") // hangs; "npx.cmd" works
.args(ImmutableList.of(
"-y", "@modelcontextprotocol/server-filesystem", "<some-dir>"))
.build();
McpToolset toolset = new McpToolset(params.toServerParameters());
List<BaseTool> tools = toolset.getTools(null).toList().blockingGet();
// blocks: ~5 min per attempt, up to 3 retries, then throws
Observed behavior
| command | result |
|---|---|
npx |
silent block, measured 900 s (~15 min) total, then McpToolLoadingException; no node.exe ever spawned |
npx.cmd |
OK in ~3.5 s, 14 tools loaded |
Workaround
Use the .cmd extension explicitly on Windows:
.command("npx.cmd")
Suggestions
- Add a Windows note to
examples/mcpfilesystem/README.md(lowest
effort, immediate relief for new users). - Optionally, fail fast with a clear error when the configured command
cannot be executed at all (e.g. probe withProcessBuilder.start()
before the 5-minute timeout), or auto-map well-known npm shims
(npx/npm/node) to their.cmdvariants on Windows.
Happy to send a PR for either suggestion. Thanks!
- Vorherrschende Sprache
- Java
- Sterne
- 1.8k
- Forks
- 440
- Ø Merge
- 3 T. 13 Std.
- Gemergte PRs (30 T.)
- 95
Entwicklungsumgebung
Startet den Dev-Container des Projekts im Browser, mit Ihrem eigenen GitHub-Konto.
- Kein Dockerfile und keine Docker-Compose-Datei
- Hat eine Pull-Request-Vorlage
- Beitragsleitfaden lesen
Erste Schritte
- Lesen Sie das ganze Issue und danach den Beitragsleitfaden des Projekts.
- Schreiben Sie ins Issue, dass Sie es übernehmen — das erspart doppelte Arbeit.
- Forken Sie das Repository und arbeiten Sie in einem Branch.
- Öffnen Sie einen Pull Request, der die Issue-Nummer nennt.
Mehr aus google/adk-java
-
InMemorySessionService.appendEvent recreates a deleted sessionEvtl. vergeben @hirematha hat das vor 4 Tagen übernommen. Offenneeds review
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 84/100
google/adk-java#1697 · 2 Kommentare · 1 zugewiesene Person ·
Maintainer antworten meist innerhalb von 1 Tag
-
Runner drops callbackContextData written in onUserMessageCallback when it resumes an invocationEvtl. vergeben @hirematha hat das vor 4 Tagen übernommen. Offenneeds review
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 78/100
google/adk-java#1695 · 1 Kommentar · 1 zugewiesene Person ·
Maintainer antworten meist innerhalb von 1 Tag
-
[spring-ai] Wrapping ChatModels without getOptions() override fail with ClassCastException when ADK tools are attachedEvtl. vergeben @hirematha hat das heute übernommen. Offen
google/adk-java#1731 · 1 zugewiesene Person ·
Maintainer antworten meist innerhalb von 1 Tag
-
AgentExecutor ignores the A2A contextId when creating a session, so multi-turn conversations start over every turnEvtl. vergeben @hirematha hat das vor 2 Tagen übernommen. Offenneeds review
google/adk-java#1718 · 2 Kommentare · 1 zugewiesene Person ·
Maintainer antworten meist innerhalb von 1 Tag
-
runLive passes partial events to appendEvent and never aggregates text chunks, unlike ADK PythonEvtl. vergeben @hemasekhar-p hat das vor 18 Tagen übernommen. Offenneeds review
Schwierigkeit 4/5 3-5 Tage Anfängerfreundlichkeit 45/100
google/adk-java#1648 · 3 Kommentare · 1 zugewiesene Person ·
Maintainer antworten meist innerhalb von 1 Tag
Alle Issues in google/adk-java
Ähnliche Issues
-
status: waiting-for-triage
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 78/100
spring-projects/spring-framework#37614 ·
Maintainer antworten meist innerhalb von 1 Tag
-
azure-spring azure-spring-aad Client
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 72/100
Azure/azure-sdk-for-java#51046 · 1 Reaktion ·
Maintainer antworten meist innerhalb von 1 Tag
-
helm-knative-apply.sh fails with Helm 4Evtl. vergeben Ein verknüpfter Pull Request ist offen oder bereits gemergt. Offenarea: triage theme: undefined
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 85/100
jhipster/generator-jhipster#35895 ·
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 78/100
Maintainer antworten meist innerhalb von 1 Tag
-
Schwierigkeit 2/5 1-3 Stunden Anfängerfreundlichkeit 85/100
oracle/graalvm-reachability-metadata#11659 ·
Maintainer antworten meist innerhalb von 1 Tag