gitlab-mcp
MCP server for GitLab: 100+ tools for projects, MRs, issues, pipelines, wikis and more via the GitLab REST/GraphQL API
Runs with mockssource: GitHubhomepageTypeScriptMITcommit 95edb4901e7d
TypeScript, MIT licensed. The project labels itself: ai, claude, cursor, devtools, gitlab, gitlab api, llm and mcp.
gitlab-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 20.1 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The @zereight/mcp-gitlab MCP server version 2.3.2 installs, builds, and passes its full mock test suite (all tests pass) using a built-in mock GitLab server that replaces the real GitLab API.
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 92 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.
- Node.js v18.19.1 was installed but package requires >=20 (from @hono/node-server dependency). npm install failed with EBADENGINE.5 minutes
- Install time
- 20 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm run test:mock exited 0 (mock test suite, ~350+ subtests all pass); npm run test:schema exited 0 (54 schema tests pass); npm run test:stateless exited 0 (107 stateless tests pass); npm run test:consumer-smoke exited 0 (pack/install smoke); echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{...}}' | timeout 5 node build/index.js returned valid MCP initialize response with serverInfo version 2.3.2
- Model tokens used
- 198,040
- Exact commit tested
- 95edb4901e7d
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
# tests 107 # suites 17 # pass 107 # fail 0 # cancelled 0 # skipped 0 # todo 0 # duration_ms 30505.698436 All tests pass, the server runs. Let me compile the final report. tokens used 198,040 All tests pass, the server runs. Let me compile the final report.
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
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 20.1 minutes to install, slower than the median of the 164 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 165 ai projects Argusic has installed and timed, gitlab-mcp was the 139th fastest to reach a running state, and 107 of 165 reached one at all.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.06 |
Topics (from GitHub)
aiclaudecursordevtoolsgitlabgitlab-apillmmcpmcp-servermodel-context-protocol
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/gitlab-mcp)Questions
- Does gitlab-mcp run?
- gitlab-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 20 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test gitlab-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 95edb4901e7d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test gitlab-mcp?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does gitlab-mcp take to install?
- 20.1 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 gitlab-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing gitlab-mcp?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does gitlab-mcp compare with the alternatives?
- Of the 165 ai projects Argusic has installed and timed, gitlab-mcp was the 139th fastest to reach a running state, and 107 of 165 reached one at all.
- Where is the evidence for gitlab-mcp?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.