modelcontextprotocol

The official MCP server implementation for the Perplexity API Platform

Runs with mockssource: GitHubhomepageTypeScriptMITcommit c58e4ad25460

TypeScript, MIT licensed.

modelcontextprotocol runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

npm install builds without errors, 90 tests pass, the HTTP server starts on port 8080 and serves health (200) and MCP tools/list (4 tools) correctly, and the STDIO server responds to tools/list via stdin.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
2
last tested
stars
2,638
forks
395
open issues
25
watchers
24
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
under a minute
Cold machine to finish
2 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
npm test: 90 passed across 4 test files; curl 127.0.0.1:8080/health returned 200; curl 127.0.0.1:8080/mcp tools/list returned 4 tools with valid JSON-RPC
Model tokens used
88,780
Exact commit tested
c58e4ad25460
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.

**Errors:** None encountered.
**Mock status:** The test suite uses mocked fetch calls and in-memory transports (vitest with `glob…
tokens used
88,780
All working. The earlier issue was just a timing/process lifecycle issue in the PTY. The server sta…
Here is my final report:
**Install:** `npm install` succeeded (245 packages). `npm run build` (tsc) compiled to `dist/`. Eng…
**Tests:** `npm test` — all 90 tests pass across 4 test files.
**HTTP server:** `node dist/http.js` with `PERPLEXITY_API_KEY=test-key` starts on `127.0.0.1:8080`.…
**STDIO server:** `node dist/index.js` with `PERPLEXITY_API_KEY=test-key` responds to `tools/list` …
**Errors:** None encountered.
**Mock status:** The test suite uses mocked fetch calls and in-memory transports (vitest with `glob…

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

  • Installed in 0.5 minutes, faster than the median of the 35 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

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.

Of the 36 TypeScript projects Argusic has installed and timed, modelcontextprotocol was the 3rd fastest to reach a running state, and 30 of 36 reached one at all.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.04
Argusic Runner1/3Runs with mocks92.000.01

Embed the badge

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

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

Questions

Does modelcontextprotocol run?
modelcontextprotocol runs, with mocks standing in for external services. 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 modelcontextprotocol?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c58e4ad25460. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test modelcontextprotocol?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does modelcontextprotocol take to install?
0.5 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 modelcontextprotocol need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing modelcontextprotocol?
Nothing did, in the recorded run: zero errors between clone and running.
How does modelcontextprotocol compare with the alternatives?
Of the 36 TypeScript projects Argusic has installed and timed, modelcontextprotocol was the 3rd fastest to reach a running state, and 30 of 36 reached one at all.
Where is the evidence for modelcontextprotocol?
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