git-mcp
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
Runssource: GitHubhomepageTypeScriptApache-2.0commit c487a29895dc
TypeScript, Apache-2.0 licensed. The project labels itself: agentic ai, agents, ai, claude, copilot, cursor, git and llm.
git-mcp runs. An Argusic agent installed it in 10 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The GitMCP app installs, builds, and serves its web UI on the react-router dev server at HTTP 200, and all 37 unit tests pass.
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.
- Install time
- 10 minutes
- Cold machine to finish
- 7 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- curl http://localhost:5200/ returned HTTP 200 with full HTML page; vitest run exited 0 with 37/37 passed; pnpm build exited 0 with client and SSR bundles
- Model tokens used
- 256,403
- Exact commit tested
- c487a29895dc
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Here's the summary of everything completed: - **Install**: `pnpm install` — 853 packages installed. Build scripts for `esbuild`, `sharp`, and `… - **Tests**: `vitest run` — 7 test files, 37 tests, all passed. - **Dev server**: `react-router dev` started on port 5200. `curl http://localhost:5200/` returned H… The only notable environment gap is Node.js v18.19.1 vs the v20 requirement — it printed warnings b… tokens used 256,403 Here's the summary of everything completed: - **Install**: `pnpm install` — 853 packages installed. Build scripts for `esbuild`, `sharp`, and `… - **Tests**: `vitest run` — 7 test files, 37 tests, all passed. - **Dev server**: `react-router dev` started on port 5200. `curl http://localhost:5200/` returned H… The only notable environment gap is Node.js v18.19.1 vs the v20 requirement — it printed warnings b…
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.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 3 times, so the result is not a one-off.
What did not, or is not known
- Took 10 minutes to install, slower than the median of the 37 comparable projects Argusic has measured.
Of the 38 agentic-ai projects Argusic has installed and timed, git-mcp was the 24th fastest to reach a running state, and 28 of 38 reached one at all.
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 10 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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/git-mcp)Questions
- Does git-mcp run?
- Yes. git-mcp runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test git-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c487a29895dc. 3 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test git-mcp?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does git-mcp take to install?
- 10 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 git-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing git-mcp?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does git-mcp compare with the alternatives?
- Of the 38 agentic-ai projects Argusic has installed and timed, git-mcp was the 24th fastest to reach a running state, and 28 of 38 reached one at all.
- Where is the evidence for git-mcp?
- All 3 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.