# MCP Git server mcp-git 2026.10.19: our test log

Canonical: https://theagenticweekly.com/tests/mcp-server-git · Last verified: 2026-10-25 · Published: 2026-10-25 · Author: Agentic Weekly (operated independently from Texas, US) · Evidence: Tested by us on 2026-10-25. Local open-weight model, not the vendor's hosted models. A smoke test on a CPU-only box, not a benchmark.

> The MCP Git server 2026.10.19 started in 512 ms, listed 12 tools and answered git_status in 3.2 ms median.

## Result at a glance

Table: MCP Git server test record

| Field | Value |
|---|---|
| Result | Passed |
| Version tested | mcp-git 2026.10.19 |
| Date and time | 2026-10-25, 22:37 CDT (America/Chicago) |
| Task | A small Python client written with the official MCP Python SDK (2.3.0) spawns the server as a child process over stdio, times the initialize handshake (cold start: spawn to initialize result), times one tools/list, then times 30 sequential tools/call requests and reports the median and 95th percentile. Numbers are milliseconds on the rig described on the methodology page. |
| Model used | none (no language model involved) |
| Hardware | Linux x86_64 virtual machine (Debian 13), 8 vCPU (Intel Xeon, 1 thread per core), 15 GiB RAM, no GPU |
| git_status on a fixture repo | cold start 512 ms; tools/list 3.6 ms (12 tools); 30 x git_status: median 3.2 ms, p95 3.7 ms |

## What we found

- 12 tools exposed: git_status, git_diff_unstaged, git_diff_staged, git_diff, git_commit, git_add, git_reset, git_log, git_create_branch, git_checkout, git_show, git_branch.
- It shells out to the git library on every call, which is why a call is a few milliseconds instead of under one like the Node servers that read files directly.

## What we ran, step by step

Table: Commands run, wall-clock time and exit code

| Step | Wall time | Exit code | Notes |
|---|---|---|---|
| Install with uv (cold, no cache) | 2.21 s | 0 | mcp-server-git            2026.10.19; 34 MB on disk; load 4.16. |
| Latency run: git_status on a fixture repo | n/a | 0 | mcp-git 2026.10.19 (protocol 2025-11-25). cold start 512 ms; tools/list 3.6 ms (12 tools); 30 x git_status: median 3.2 ms, p95 3.7 ms. Load 2.38. |

Exact commands (paths shortened)

```
# Install with uv (cold, no cache)
uv venv -q -p 3.13 work/pymcp/mcp-server-git && VIRTUAL_ENV=work/pymcp/mcp-server-git uv pip install --no-cache -q mcp-server-git

# Latency run: git_status on a fixture repo
work/pymcp/mcp-server-git/bin/mcp-server-git
```

## Raw output (excerpts)

Output of the timed call (git_status on a fixture repo), first 300 characters

```
git_status({"repo_path": "/workspace/tests2/work/gitrepo"})
Repository status:
On branch master
nothing to commit, working tree clean
```

## Gotchas and things that broke

- The server needs an explicit repo_path argument on each call; the model has to supply it.

## What we did not test

- Remote (HTTP) transport, authentication and concurrent clients: only local stdio with one client was measured.
- Large payloads: calls used tiny inputs, so these latencies are protocol and process overhead, not throughput.
- Anything about answer quality: no model was involved in the latency numbers.
- These are single smoke-test runs; it is not a benchmark. The machine was shared with other jobs.

## Reproduce it

Versions change. These commands install whatever is latest on the day you run them unless a version is pinned, so expect different results later. The version we measured is in the table above.

```
VIRTUAL_ENV=.venv uv pip install mcp-server-git
.venv/bin/mcp-server-git
```

## How to read this test

Every number on this page was measured on this one machine, which also ran other jobs, so timings are indicative and vary run to run. A pass means our small task worked once or as stated, a fail means it did not work as we ran it; neither says how the tool behaves with a vendor's frontier model, on a GPU, or at scale. Where a tool could not run without an account or a GPU, we say so instead of guessing.

See the [testing rig](https://theagenticweekly.com/methodology#testing-rig) for the hardware, the local model and the rules we follow, and the [test hub](https://theagenticweekly.com/tests) for every other test.

## Sources

- [MCP reference servers repository](https://github.com/modelcontextprotocol/servers) (fetched 2026-10-25)

## Related

- [All test logs](https://theagenticweekly.com/tests)
- [Methodology and testing rig](https://theagenticweekly.com/methodology#testing-rig)
- [Study: MCP server startup and call latency over stdio](https://theagenticweekly.com/research/mcp-servers-latency-and-failures)
- [MCP servers facts and sources](https://theagenticweekly.com/tools/mcp-servers)

## How to cite

Agentic Weekly, "MCP Git server mcp-git 2026.10.19: our test log", last updated 2026-10-25, https://theagenticweekly.com/tests/mcp-server-git