npx -y @hypnosis/ssh-mcp-server

claude mcp add ssh -s user \
  -e SSH_PROFILES_FILE="$HOME/.claude/ssh-profiles.json" \
  -- npx -y @hypnosis/ssh-mcp-server

{
  "mcpServers": {
    "ssh": {
      "command": "npx",
      "args": ["-y", "@hypnosis/ssh-mcp-server"],
      "env": {
        "SSH_PROFILES_FILE": "~/.claude/ssh-profiles.json"
      }
    }
  }
}

{
  "profiles": {
    "production": {
      "host": "server.example.com",
      "username": "admin",
      "privateKeyPath": "~/.ssh/your_private_key"
    }
  }
}

/plugin marketplace add hypnosis/ssh-mcp-server
/plugin install ssh-mcp-server@ssh-mcp-server

scp app.conf router:/etc/
# scp: subsystem request failed on channel 0

$ uptime
 10:42:17 up 18 days,  3:21,  2 users,  load average: 0.42, 0.31, 0.28
$ df -hT
Filesystem     Type   Size  Used Avail Use% Mounted on
/dev/sda1      ext4    40G   35G  5.0G  87% /
overlay        overlay  40G   35G  5.0G  87% /var/lib/docker/overlay2/...
$ free -h
               total        used        free      shared  buff/cache   available
Mem:           7.7Gi       4.9Gi       612Mi       121Mi       2.2Gi       2.5Gi
$ systemctl --failed
  UNIT              LOAD   ACTIVE SUB    DESCRIPTION
● api-worker.service loaded failed failed API background worker
$ docker ps -a
CONTAINER ID   IMAGE          STATUS                     PORTS
8e14d0b41c2a   api:latest     Up 3 minutes               0.0.0.0:8080->8080/tcp
65b894af2430   worker:latest  Exited (1) 2 minutes ago
$ ss -tulpn
Netid  State   Local Address:Port   Process
tcp    LISTEN  0.0.0.0:22          users:(("sshd",pid=842,fd=3))
tcp    LISTEN  0.0.0.0:8080        users:(("docker-proxy",pid=1942,fd=4))
$ journalctl -p err --since -1h | tail -50
Aug 20 10:39:14 prod api-worker[22104]: database connection timed out
Aug 20 10:39:14 prod systemd[1]: api-worker.service: Failed with result 'exit-code'.

ssh_snapshot({ "profile": "production" })

{
  "disk_pct": 87,
  "mem_pct": 64,
  "cpu_pct": 12,
  "load": "0.42 0.31 0.28",
  "containers": 7,
  "ports": 14,
  "services_running": 3,
  "recent_errors": 21,
  "unavailable": []
}

$ grep -i "timeout" /var/log/nginx/error.log
2026/08/20 10:38:54 [error] upstream timed out while reading response header
$ grep -i "timeout" /var/log/syslog
Aug 20 10:39:14 prod api-worker[22104]: database connection timed out
$ grep -i "timeout" /var/log/app/*.log 2>/dev/null
$ journalctl -u api --since "1 hour ago" | grep -i timeout
Aug 20 10:39:14 prod api[22104]: database connection timed out after 30000ms

ssh_log_search({ "profile": "production",
                 "path": ["/var/log/nginx/error.log", "/var/log/syslog", "/var/log/app/*.log"],
                 "query": "timeout", "context": 2, "since": "1h" })

{
  "matches": 34,
  "lines": [
    { "file": "/var/log/nginx/error.log", "line": 4821,
      "text": "upstream timed out while reading response header", "context": false },
    { "file": "/var/log/nginx/error.log", "line": 4822,
      "text": "client closed connection", "context": true }
  ],
  "files_searched": 6,
  "files_unreadable": ["/var/log/app/private"],
  "files_skipped": 12,
  "files_undated": [],
  "limited": false,
  "truncated": false
}

$ sudo sh -c 'cat > /etc/nginx/conf.d/api.conf' `
truncated the old file before the first byte of the new one arrived. If the connection drops
mid-write, the service is left with a partial config.

#### Structured MCP result

// Code block

#### What the agent gains

| Raw SSH | Structured MCP | Your gain |
|---|---|---|
| The target is truncated before the copy completes | A complete temp file replaces it with one rename | No half-written config |
| Exit code only | Bytes and verification outcome are named | You know what actually landed |
| Permissions live inside shell text | `sudo`, `mode` and `verify` are per-file fields | Predictable ownership and fewer quoting mistakes |

`verified` has three honest outcomes: `verified`, `unavailable` when the server has no hash
tool, and `skipped` when verification was not requested. For reads, `ssh_file_read` accepts a
list of paths; `ssh_file_list` handles globs, recursion, sizes and modes.

### Run batch SSH commands with sudo

> **Situation:** A deploy is ready, but nginx syntax, service state and recent errors must all
> be checked before traffic moves. One failed check should not disappear inside a combined dump.
>
> **Question:** “Did every preflight check pass?”

#### Raw SSH

Three connections return three unrelated outputs. If the commands are joined with `;`, the
shell reports only the last exit code; if they are joined with `&&`, later checks disappear
after the first failure.

#### Structured MCP result

// Code block

#### What the agent gains

| Raw SSH | Structured MCP | Your gain |
|---|---|---|
| Three calls and unrelated outputs | One ordered command list | Fewer round trips |
| A combined shell can hide intermediate status | Every command keeps its own `exit_code` | No missed failed check |
| `sudo` and quoting are repeated in command text | `sudo` applies to the whole batch | Fewer quoting mistakes |

The destructive-command guard checks the complete list before the first command runs. If one
entry is refused, every other entry is marked as not run and nothing is sent to the server.

Each command carries its own `stdout` and `stderr`. A command that ran and printed nothing
has an empty string; a command that never ran has no such field at all, so the two cannot be
confused. Output over 128 KB per command keeps both ends — the head for tables, the tail for
logs — with a seam in between naming the amount, and `clipped_bytes` says how much was cut.
Cutting happens on byte boundaries and steps back to the edge of a character, so a clipped
answer never carries a replacement mark.

`sudo` reaches the server without a terminal: the profile's answer is handed to `sudo` on
standard input. Which secret that is comes from `sudoPassword` when the profile names one and
from `password` otherwise — a profile that logs in by key has no login password at all, and
where a machine keeps the two apart the login one is the wrong answer. Where there is nothing
to answer with, the reply says so and names the ways out, instead of leaving sudo's own advice
about `-S` and askpass helpers. A command that reads its own standard input is never given the
password, which would otherwise end up mixed into the data.

### Run long-lived SSH jobs

> **Situation:** A backup or migration will run longer than the agent session. The connection
> may close, but you still need its state, output and exit code later.
>
> **Question:** “Will this job survive the conversation?”

#### Raw SSH

The terminal is gone. You now have to reconnect, find the process, inspect the target file
and guess whether the backup finished or stopped halfway.

#### Structured MCP result

// Code block

#### What the agent gains

| Raw SSH | Structured MCP | Your gain |
|---|---|---|
| The job is tied to one SSH session | The remote job has a persistent id | Safe disconnects and restarts |
| Reconnecting means searching processes and files | Status and exit code have named states | No guessing whether it finished |
| Reading output again repeats old text | Output continues from a byte offset | Lower token use on long jobs |

Job state lives on the remote disk, not in this server's memory. `ssh_job_status` distinguishes
`running`, `finished` and `lost`; `ssh_job_output` continues from the last byte offset; and
`ssh_job_kill` signals the whole process group instead of only its shell.

### Transfer files to legacy routers and NAS devices

> **Situation:** A current OpenSSH client tries SFTP, but the router or NAS only understands
> the classic scp protocol. The file must still arrive intact and replace its target safely.
>
> **Question:** “Can this old device still receive a verified file?”

#### Raw SSH

The usual next step is to remember the legacy flag, retry the copy and then run a separate
hash command—if the device has a hash tool at all.

#### Structured MCP result

// Code block

#### What the agent gains

| Raw SSH | Structured MCP | Your gain |
|---|---|---|
| Modern SFTP mode stops at the first error | Classic scp fallback is automatic and remembered | Old gear still works |
| A successful copy does not prove integrity | SHA-256 verification has a named outcome | Corruption is not mistaken for success |
| Direct replacement can leave a partial target | A temp file is moved into place after transfer | The working file survives interruptions |

If the device has neither `sha256sum` nor `openssl`, the result says `unavailable` and names
the reason instead of reporting a false match. Whole directories use `recursive: true` and
verify their hashes in one batch.

## Destructive command protection for AI agents

The guard runs locally, before a command reaches SSH. It separates operations that can be
recovered from those that destroy the container holding the data, and it checks command order
inside chains and batches.

### Stop a destructive chain before it starts

A safe backup-and-replace sequence:

The same operations in the wrong order:

The shell would delete the directory and only then discover that the backup source is gone.
The guard sees that later steps read a target already destroyed by an earlier step, so the
whole call stays on your machine. The same check catches
`dropdb app && pg_dump app > backup.sql`.

### Refuse irreversible loss, warn about recoverable changes

| Refused — the container itself | Only warned — its contents |
|---|---|
| `DROP DATABASE`, `dropdb` | `DROP TABLE`, `TRUNCATE`, `DELETE FROM` |
| `docker volume rm`, `docker compose down -v` | `docker rm -f ` |
| `crontab -r` | editing one job |
| `mkfs`, `wipefs -a`, `lvremove`, `zfs destroy` | `chmod 777` |
| `reboot`, `shutdown`, `halt` | `git reset --hard` |

`docker compose down -v` is refused because `-v` removes named Docker volumes, including a database
volume. Without `-v`, stopping the services is not treated as the same irreversible action.

Recursive deletion of the filesystem root, a home directory or system trees such as `/etc`,
`/var` and `/usr` is also refused, including when a symlink leads there. An unresolved target
such as `rm -rf "$DIR"/*` is refused too: "could not check" is not treated as "safe".

### Name what you stop

A command that finds its target instead of naming it is not sent. The server expands it and
answers with what stands behind the target:

For a process the answer adds the signs that it is in use: how long it has been running,
which ports it accepts connections on, how many connections it is carrying. Named targets
cost nothing extra and go through in silence — `docker kill web-1`, `kill 4871`,
`systemctl stop app`.

To go ahead, name what is being stopped. The names are checked against what the command
actually reaches, so a mask that has drifted onto something else is refused rather than
confirmed:

A pattern over command lines is a case of its own. It matches the very command that carries
it, so the shell running it is signalled before the target and the reply breaks off in the
middle. Such a strike is not confirmed but rewritten — by number, or with one character
written as a class so the pattern stops matching itself:

Three outcomes stay apart: targets found, the expansion reached nothing, and nothing to ask
with — no engine on the machine, a clipped answer, a connection that failed. The last two
are refusals as well: not knowing is not a reason to proceed.

### Confirm an intentional destructive command

Nothing is forbidden permanently. Add `# CONFIRMED-DESTRUCTIVE` to a reviewed command and it
is allowed through. When the guard refuses one entry in a batch, the complete batch stops
before execution, so the server is never left after a half-run operation.

The guard works within a single call. It cannot connect a delete in one invocation with a
read in the next, or reason about tools it does not recognize. It is a seatbelt, not a policy
engine: recoverable operations remain your call. Path restrictions and quoting rules are
documented in **[docs/security.md](docs/security.md)**.

## Tools

18 SSH MCP tools for server operations. Full parameters and examples live in
**[docs/tools.md](docs/tools.md)**.

| Tool | What it does |
|---|---|
| `ssh_exec` | Run one command or a batch, with the destructive-command guard and optional detach |
| `ssh_file_read` | Read one or several files, text or binary |
| `ssh_file_write` | Write files with atomic rename and optional SHA-256 verification |
| `ssh_file_list` | List a directory, with optional glob and recursion |
| `ssh_upload` | Upload a file or directory over SSH, binary-safe with integrity checks; a directory replaces the target or merges into it |
| `ssh_download` | Download a file or directory over SSH, binary-safe with integrity checks |
| `ssh_job_status` | State of a background job: running, finished, or lost |
| `ssh_job_output` | Read accumulated output from a byte offset |
| `ssh_job_list` | List jobs, sweeping finished ones past their TTL |
| `ssh_job_kill` | Signal a job's whole process group |
| `ssh_log_tail` | Last N lines of one or several logs, glob supported; a container by name |
| `ssh_log_search` | Pattern search across logs, or through a container's log |
| `ssh_snapshot` | One-shot health snapshot: services, resources, Docker, network, errors |
| `ssh_monitor` | Transport control: stats, reload, test, list, close |
| `ssh_audit_baseline` | System, disk, memory, network, ssh, services, Docker, firewall, updates |
| `ssh_tls_check` | Certificate expiry, SAN, chain and renewal hook for a domain |
| `ssh_disk_breakdown` | Where the disk went: `du` top-N, Docker, journald, caches |
| `ssh_service_status` | `systemctl status` plus a `journalctl` tail for one unit |

### MCP tool safety annotations

Standard MCP annotations tell clients which tools are read-only, destructive, idempotent or
open-world. See the [full table](docs/tools.md#what-each-tool-declares-about-itself).

### Run SSH commands and manage remote files

Commands, file reads and writes, directory listings — the ordinary work on a machine, each
answer already parsed.

### Monitor long-running SSH jobs

Slow work is detached and followed instead of waited for: every look says how far it got.

### Search logs and check server health

Logs of files and containers, and a one-shot picture of the machine, with output capped so
a tail does not eat the context window.

### Upload and download files over SSH

Binary-safe transfers with integrity checks. Details in [docs/transfer.md](docs/transfer.md).

> **For binaries and large files use `ssh_upload` / `ssh_download`** — base64 chunks and
> heredocs are not binary-safe or atomic.

### Audit Linux servers over SSH

Read-only and batched into one round trip. Details in [docs/audit.md](docs/audit.md).

### Windows SSH compatibility mode

Windows uses compatibility mode automatically. When connection multiplexing is
unavailable, the server switches to one connection per command. The same tools remain
available over key-based SSH — no separate setup or Windows-specific implementation.

The destructive-command guard is covered in [Destructive command protection for AI agents](#destructive-command-protection-for-ai-agents).

## Set up the SSH MCP server

Run the package from [Install in 30 seconds](#install-in-30-seconds) first, then create a
profile file.

### Create SSH connection profiles

Put it wherever you like — next to your agent's own config is the usual choice. The examples below use `~/.claude/ssh-profiles.json`; for other agents swap the directory (`~/.codex/`, `~/.qwen/`, `~/.config/opencode/`):

**Choose an SSH profile explicitly**

There is no profile the server falls back to: each one is a different machine, and a command
sent to the wrong machine is not something an error message can undo afterwards. Ask without
a name and the answer lists the names to choose from:

A profile the server cannot use for SSH — no `host`, no `username`, or `mode: "local"` — is skipped without complaint, and fields it does not recognize are left alone, so the file can be shared with other tools. A profile with a **broken** field is a different case: it is named along with the field and the value, and its healthy neighbors keep working.

Each profile optionally takes a `pathSecurity` block that whitelists or blacklists the paths file tools may touch — see [docs/security.md](docs/security.md#path-security).

A profile that logs in by key but needs `sudo` on the far side takes a `sudoPassword` — the secret `sudo` is answered with, which on many machines is not the login password. Keep it in the secrets file rather than here.

### Keep SSH passwords and passphrases out of profiles

Prefer keys. If a password or encrypted-key passphrase is unavoidable, keep it in a separate
secrets file, never in the profile itself:

The secrets file is keyed by profile name — see [secrets.json.example](secrets.json.example):

`sudoPassword` is what `sudo` is answered with on that machine. A profile logging in by key
has no login password to offer, and where the two differ the login one is the wrong answer;
without it, `password` is used.

The secrets file must be readable only by you (`chmod 600`). Relative paths resolve from the
profiles file; secrets stay out of `argv` and are masked in logs. See
[credentials security](docs/security.md#credentials-keep-the-secret-out-of-the-profiles-file).

### Configure Claude Code, Codex and other MCP clients

Choose the client you use and point it at the same profiles file.

**Claude Code**

One command; `-s user` makes the server available in every project:

**Codex CLI**

**opencode**

Put it in `~/.config/opencode/opencode.json`:

**Qwen Code**

One command, same as the others:

**Other MCP clients**

Gemini CLI, Hermes, Cline, an editor plugin or your own agent work the same way. All they
need is a command to run and one environment variable.

### Restart your MCP client

Restart the client, then run `ssh_monitor({ action: "list" })` to confirm the profile loaded.

## SSH MCP server configuration

| Variable | What it does | Default |
|---|---|---|
| `SSH_PROFILES_FILE` | Path to the profiles JSON — **required** | — |
| `SSH_MCP_LOG_LEVEL` | `debug`, `info`, `warn`, `error` | `info` |
| `LOG_LEVEL` | Fallback, used only when `SSH_MCP_LOG_LEVEL` is unset | `info` |
| `SSH_MCP_LOG_TIMESTAMP` | Timestamps in log lines | `true` |
| `SSH_MCP_CONTROL_PERSIST` | Seconds a shared connection stays alive after the last command; `0` closes it at once | `600` |
| `SSH_MCP_CONTROL_DIR` | Where control sockets live | `~/.ssh/ssh-mcp` |
| `SSH_MCP_PROFILES_CACHE_TTL` | Profile cache TTL, ms | `60000` |
| `SSH_MCP_PROFILES_WATCH` | Reload the profiles file when it changes | `true` |

The shared connection outlives this process on purpose: closing it on exit would cut the channel another window on the same machine is using.

## SSH MCP server limitations

**Every limit tells you the way around it.** A tool that cannot do something says so and
names `ssh_exec`, which runs commands on the machine directly — an unsupported log driver,
a utility the machine does not have, an engine this server does not speak. You do not have
to know in advance where the tools end: the refusal says it, at the moment it matters.

Three refusals deliberately stay silent about the shell, because there it is the wrong
answer: a path your profile forbids (walking around your own rule is not a fix), a
malformed call (the fix is in the call), and a refusal from `ssh_exec` itself.

- **Cancellation:** a cancelled call now stops the command on the server too, sent as a second call over the same connection. Where the server has no `/proc`, the command is found through `ps` instead. FreeBSD is not verified: correct behaviour there is not guaranteed. File transfers and `ssh_snapshot` do not take cancellation at all.
- **Atomic writes:** BSD and macOS cannot pre-check cross-filesystem renames.

## SSH MCP server roadmap

- [ ] Full test run against macOS SSH hosts
- [ ] End-to-end compatibility run on Windows
- [ ] Multi-host audits — compare health across several SSH profiles in one call
- [ ] Import profiles from the existing `~/.ssh/config`
- [ ] Resumable transfers for large files and unstable connections
- [ ] Remote operation timeline — commands, transfers and guard decisions in one audit trail
- [ ] Ready-made SSH troubleshooting playbooks

- [x] ~~Container logs without dropping to the shell~~ — **DONE:** `ssh_log_tail` and `ssh_log_search` take a container name, ask docker where it writes and read that file with the same machinery as any other log
- [x] ~~A refusal that leaves you stuck~~ — **DONE:** every limit now names `ssh_exec` as the way through, so hitting the edge of a tool costs one sentence instead of a guessing game
- [x] ~~Answers that reach the model~~ — **DONE:** command output, matched log lines, machine names and snapshot sections travel in the fields, not only in the text
- [x] ~~Smaller MCP tool schemas~~ — **DONE:** the tool list got 10% lighter, and a detached job now shows the last lines it wrote instead of being polled blind
- [x] ~~Long work under root~~ — **DONE:** a detached job runs with `sudo` and is followed as root, and a key-only profile answers `sudo` with its own `sudoPassword`

## Develop and test the SSH MCP server

The live suite runs against real containers — one BusyBox, one coreutils — because the two disagree quietly, and a mock agrees with whoever wrote it. See [docs/architecture.md](docs/architecture.md) for the layout.

## Like SSH MCP Server? ⭐

If you like the tool, [give it a star on GitHub](https://github.com/hypnosis/ssh-mcp-server) — it helps more people discover the project.

## Contribute to the SSH MCP server

Issues and pull requests are welcome at [github.com/hypnosis/ssh-mcp-server](https://github.com/hypnosis/ssh-mcp-server).

## License

MIT — see [LICENSE](LICENSE).