mcp-ssh-manager
MCP server for SSH: let Claude Code, Codex and any MCP client run commands, transfer files and manage servers over SSH, with human approval, an encrypted vault and a live audit trail. Desktop app and CLI included.
Runs with mockssource: GitHubhomepageJavaScriptMITcommit 0ec433a23834
JavaScript, MIT licensed. The project labels itself: agentic ai, ai agents, anthropic, audit log, claude code, claude desktop, devops and human in the loop.
mcp-ssh-manager runs, with stand-ins for the services it depends on. An Argusic agent installed it in 12 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Installed dependencies, passed the full npm test suite (all groups Failed: 0), passed typecheck and the project's validate.sh, and the MCP server answered initialize as mcp-ssh-manager 3.8.5 (37 tools listed) and executed commands end-to-end against a local mock SSH server with success true and code 0; only the optional Bash CLI remains unlaunchable because the container lacks the system ssh binary.
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 82 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.
- cli/install.sh fails: missing required system 'ssh' binary (container has no openssh-client, no root to install it; apt-get fails with Permission denied on dpkg lock)4 minutes
- MCP tools/list answered -32601 immediately after initialize (server registers tools only after configuration load); no code defect, my probe needed a startup delay before tools/call3 minutes
- Install time
- 12 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- npm test exited 0 with all groups Failed: 0; MCP e2e harness: initialize -> 'mcp-ssh-manager 3.8.5', tools/list -> 37 tools, tools/call ssh_list_servers -> e2ehost config returned, tools/call ssh_execute(hostname) -> stdout 'mock:demo:timeout 120 sh -c 'hostname'', code 0, success true; npm run typecheck exit 0; ./scripts/validate.sh exit 0
- Model tokens used
- 383,139
- Exact commit tested
- 0ec433a23834
- 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
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 attempt that decided the verdict above. 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.
tokens used
383,139
Everything is verified. No repository changes remain (clean `git status`), and every test group rep…
**Summary of the run**
- **Environment:** Node v18.19.1, npm 9.2.0, Git available; no root, no system package installs pos…
- **Standard install:** `npm install` succeeded twice — in `/work/repo` (220 packages, warnings onl…
- **Test suite:** `npm test` exits 0 in both the repo and the fresh clone; every test group reports…
- **Real app launch (MCP server over stdio):** `node src/index.js` answered MCP `initialize` with `…
- **End-to-end with mock:** I stood up a real `ssh2` SSH server on a local port (generated ECDSA ho…
- **Gap:** the `ssh-manager` Bash CLI could not be launched because the container lacks the system …
- **Notes:** `npm install` prints 13 `npm audit` vulnerabilities and EBADENGINE warnings for two tr…
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 12, "e…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
- Licensed MIT, as reported by its host.
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.
- Took 12 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
- Hit 2 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 10 anthropic projects Argusic has installed and timed, mcp-ssh-manager was the 6th fastest to reach a running state, and 5 of 10 reached one at all.
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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 82.00 | 0.09 |
Topics (from GitHub)
agentic-aiai-agentsanthropicaudit-logclaude-codeclaude-desktopdevopshuman-in-the-loopllm-toolsmcpmcp-servermcp-sshmodel-context-protocolopenai-codexremote-accesssecuritysftpsshssh-clientssh-mcp
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-ssh-manager)Questions
- Does mcp-ssh-manager run?
- mcp-ssh-manager runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 12 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test mcp-ssh-manager?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0ec433a23834. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp-ssh-manager?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-ssh-manager take to install?
- 12 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-ssh-manager need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-ssh-manager?
- 2 things 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-ssh-manager compare with the alternatives?
- Of the 10 anthropic projects Argusic has installed and timed, mcp-ssh-manager was the 6th fastest to reach a running state, and 5 of 10 reached one at all.
- Where is the evidence for mcp-ssh-manager?
- 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.