12306-mcp

This is a 12306 ticket search server based on the Model Context Protocol (MCP).

Runssource: GitHubJavaScriptMITcommit ff6439da6f63

JavaScript, MIT licensed. The project labels itself: 12306, mcp, mcp server and train tickets.

12306-mcp runs. An Argusic agent installed it in 1 minute and hit no errors on a clean machine with no GPU, and the whole session was recorded.

npm install and tsc build pass, the MCP server starts in both stdio and HTTP modes, and all 8 tools respond correctly including real calls to the 12306 API for ticket queries and station data.

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

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.02 (measured)
recorded runs
2
last tested
stars
2,451
forks
341
open issues
14
watchers
7
size
1 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
1 minutes
Cold machine to finish
4 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
node build/index.js started in stdio mode and responded to MCP JSON-RPC tools/list (8 tools), tools/call get-current-date returned '2026-11-11', tools/call get-stations-code-in-city returned 64 stations, and tools/call get-tickets contacted real 12306 API; HTTP mode on port 8080 served SSE endpoint with session events
Model tokens used
93,207
Exact commit tested
ff6439da6f63
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.

All steps completed with no errors. Here's the summary:
**Install**: `npm install` and `tsc` build both succeeded (some engine warnings for optional dev de…
**Stdio mode verified**:
- Server starts and prints `"12306 MCP Server running on stdio @Joooook"`
- `tools/list` → returns 8 MCP tools (get-current-date, station lookups, get-tickets, get-interline…
- `get-current-date` → returns `"2026-11-11"`
- `get-stations-code-in-city("北京")` → returns 64 stations with codes
- `get-tickets("2026-11-11", "北京" → "上海")` → contacted the real 12306 API and returned results
**HTTP mode verified**:
- Server starts on `--port 8080` with both SSE (`/sse`) and Streamable HTTP (`/mcp`) endpoints
- SSE endpoint returns proper `event: endpoint`, `data: /message?sessionId=...` events
No errors were encountered. The project works as a brand-new install with no fixes needed.

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 1 minute.
  • 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 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 1 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.02
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

12306mcpmcp-servertrain-tickets

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/12306-mcp.svg)](https://argusic.com/subject/12306-mcp)

Questions

Does 12306-mcp run?
Yes. 12306-mcp runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test 12306-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ff6439da6f63. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test 12306-mcp?
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 12306-mcp take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does 12306-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing 12306-mcp?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for 12306-mcp?
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.

Discussion