mcp-remote
Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server.
Runssource: GitHubhomepageTypeScriptMITcommit 6a06aca546a8
TypeScript, MIT licensed. The project labels itself: mcp.
mcp-remote runs. An Argusic agent installed it in 20 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 490 unit/integration tests pass, all 8 concurrent-instance OAuth tests pass with the local OAuth simulator, all 2 real E2E tests connect to Cloudflare and Hugging Face MCP servers, all 4 protocol-era bridge tests pass, and the dist build runs without toWellFormed errors on Node 18
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- [email protected] calls String.prototype.toWellFormed() which is only available in Node.js 20+, but the container has Node.js 18.19.115 minutes
- Install time
- 20 minutes
- Cold machine to finish
- 40 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pnpm test: 490 passed (15 files); test/ concurrent-instances: 8/8 passed; test/ authorize-params: 1/1 passed; test/ e2e: connected to Cloudflare and Hugging Face real MCP servers; test/ protocol-era: 4/4 passed; dist/proxy.js runtime: no toWellFormed errors
- Model tokens used
- 248,554
- Exact commit tested
- 6a06aca546a8
- 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.
Here's the complete summary of everything I did and observed: **Install & Build**: Successfully installed dependencies with `npx pnpm install` and built with `np… **Error encountered -- `value.toWellFormed is not a function`**: `[email protected]` calls `String.prot… **Fix applied**: Created `src/lib/toWellFormedPolyfill.js` as a plain JS module (no TypeScript inte… **Verification results**: - `pnpm test` -- **15/15 test files passed, 490/490 tests passed** (unit + integration tests in `sr… - `test/` concurrent-instances test -- **8/8 passed** (OAuth simulator, real process spawning) - `test/` authorize-params test -- **1/1 passed** - `test/` e2e test (Cloudflare real server) -- **passed** - `test/` e2e test (Hugging Face real server) -- **passed** - `test/` protocol-era test -- **4/4 passed** - `node dist/proxy.js` running against localhost -- **no more `toWellFormed` errors**
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.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 20 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 12 mcp projects Argusic has installed and timed, mcp-remote was the 11th fastest to reach a running state, and 10 of 12 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.
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/mcp-remote)Questions
- Does mcp-remote run?
- Yes. mcp-remote runs. Argusic installed and launched it on a clean machine in 20 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test mcp-remote?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6a06aca546a8. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp-remote?
- The run that produced this verdict cost $0.19: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-remote 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 mcp-remote need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-remote?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does mcp-remote compare with the alternatives?
- Of the 12 mcp projects Argusic has installed and timed, mcp-remote was the 11th fastest to reach a running state, and 10 of 12 reached one at all.
- Where is the evidence for mcp-remote?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.