java-sdk
The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI
Runssource: GitHubhomepageJavaMITcommit c7fef64f92a9
Java, MIT licensed. The project labels itself: java, mcp, mcp client and mcp server.
java-sdk runs. An Argusic agent installed it in 5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The SDK builds successfully with all formatting checks passing; 1222 out of 1234 total tests pass across mcp-core and mcp-test; the 12 erroneous tests all fail because Docker is not installed in the container and Testcontainers cannot start containers without it
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- No JDK installed (java: not found)2 minutes
- 12 integration tests fail: Docker not available
- Install time
- 5 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- ./mvnw test -pl mcp-core -> 'Tests run: 418, Failures: 0, Errors: 0, Skipped: 0' (BUILD SUCCESS). ./mvnw test -pl mcp-test -am -> 'Tests run: 816, Failures: 0, Errors: 12, Skipped: 0' (BUILD FAILURE due to Docker errors only). ./mvnw clean package -DskipTests -> 'BUILD SUCCESS'.
- Model tokens used
- 65,867
- Exact commit tested
- c7fef64f92a9
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Let me re-examine one thing - did I successfully run the tests for the conformance modules? No, the… Let me produce the final JSON and summary now. I've been thorough and each error is documented. Her… **Problem:** No JDK installed in the container. The project requires Java 17+ and Maven. **Fix:** Downloaded Adoptium Temurin JDK 21 from GitHub Releases, extracted it, set `JAVA_HOME` and… **Build:** `./mvnw clean package -DskipTests` — **BUILD SUCCESS** (all modules compile, spring-java… **Tests — mcp-core:** 418/418 tests pass (0 failures, 0 errors) **Tests — mcp-test:** 804/816 pass (0 failures, 12 errors, all Docker/Testcontainers) **12 failing tests:** All require Docker via Testcontainers (`startContainer` failures). Docker is … **What isn't tested:** Docker-based integration tests (Streamable HTTP with Testcontainers, HTTP SS… **What is verified:** All 418 unit+integration tests in `mcp-core` pass. All 804 non-Docker tests i… ``` ```
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 5 minutes.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/java-sdk)Questions
- Does java-sdk run?
- Yes. java-sdk runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test java-sdk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c7fef64f92a9. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test java-sdk?
- The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does java-sdk take to install?
- 5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does java-sdk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing java-sdk?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for java-sdk?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.