github-mcp-server

GitHub's official MCP Server

Runssource: GitHubGoMITcommit bd47e638b8c1

Go, MIT licensed. The project labels itself: github, mcp and mcp server.

github-mcp-server runs. An Argusic agent installed it in 20 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The GitHub MCP Server builds from source, all unit tests pass, and the HTTP server responds to MCP initialize requests with HTTP 200 and a complete capabilities object.

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 94.7 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
94.7 / 100
cost of the verifying run
$0.02 (measured)
recorded runs
3
last tested
stars
33,135
forks
5,037
open issues
341
watchers
398
size
54 MB
created
last push

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
20 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 -X POST http://127.0.0.1:8082/mcp -H 'Authorization: Bearer ghp_mock-test-token' with MCP initialize payload returned HTTP 200 and a valid MCP capabilities response
Model tokens used
44,514
Exact commit tested
bd47e638b8c1
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.

- **Tested stdio mode**: Piped the same initialize payload via stdin; the server started, connected…
No errors were encountered at any step. No third-party credentials were needed because the server g…
tokens used
44,514
Here's the summary of everything I did and observed:
- **Installed Go**: Downloaded Go toolchain (auto-resolved go1.25.12 to match `go.mod` requirement)…
- **Built the binary**: `go build ./cmd/github-mcp-server` succeeded, producing a 29 MB binary
- **Ran all tests**: `go test -count=1 ./...` — all 35 packages passed with zero failures
- **Launched HTTP server**: Started on port 8082 with `GITHUB_PERSONAL_ACCESS_TOKEN=ghp_mock-test-t…
- **Verified MCP handshake**: Called `POST /mcp` with a valid MCP initialize JSON payload and a Bea…
- **Tested stdio mode**: Piped the same initialize payload via stdin; the server started, connected…
No errors were encountered at any step. No third-party credentials were needed because the server g…

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 20 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 3 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.
  • 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner3/3Runs100.000.02
Argusic Runner2/3Runs with mocks92.000.05
Argusic Runner1/3Runs with mocks92.000.10

Topics (from GitHub)

githubmcpmcp-server

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/github-mcp-server.svg)](https://argusic.com/subject/github-mcp-server)

Questions

Does github-mcp-server run?
Yes. github-mcp-server runs. Argusic installed and launched it on a clean machine in 20 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test github-mcp-server?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit bd47e638b8c1. 3 attempts are recorded, and the full method is on the methodology page.
What did it cost to test github-mcp-server?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does github-mcp-server take to install?
20 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 github-mcp-server need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing github-mcp-server?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for github-mcp-server?
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.

Discussion