Provider-neutral MCP server for AgentDispatch.
Free
Nothing to run from here
Simple Ssh is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
MCP server for SSH/SFTP remote operations
Quickstart
# 1 — run it from where its publisher ships it
npx -y simple-ssh-mcp-server
# 2 — the plan is chosen at checkout, in the browser
# 3 — ask your agent something
> MCP server for SSH/SFTP remote operations
Publishernot claimed
BHAll 3 servers
bhayanak3 servers
3 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Simple Ssh as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add simple-ssh-mcp -- npx -y simple-ssh-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
This is a paid listing, so the CLI has to be signed in and the licence has to be on your account — how the login works. Until then the install stops with the price rather than half-writing a config entry.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
49 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List Docker or Podman containers on the remote host with status, ports, and resource usage.
Takes no parameters.
Example callreturns →
View Docker or Podman container logs with tail, time filtering, and pattern matching options.
Takes no parameters.
Example callreturns →
Run a command inside a running Docker or Podman container on the remote host.
Takes no parameters.
Example callreturns →
Run a command on a connected remote server and return stdout, stderr, and exit code. Requires a sessionId from ssh_connect.
Takes no parameters.
Example callreturns →
Run a command with sudo privileges on the remote server. Password sent via stdin, never logged.
Takes no parameters.
Example callreturns →
Start a long-running command in the background for async polling. Returns a jobId. Only use when user explicitly wants background/async execution.
Takes no parameters.
Example callreturns →
Fetch output from a background job previously started with ssh_exec_background. Requires jobId.
Takes no parameters.
Example callreturns →
List all active background jobs and their status for a specific session.
Takes no parameters.
Example callreturns →
Stop/kill a background job previously started with ssh_exec_background. Requires a valid jobId — do NOT use for anything else.
Takes no parameters.
Example callreturns →
Locate files on the remote server by name pattern (like Linux find). Use when asked to find, locate, or search for a file by name or path.
Takes no parameters.
Example callreturns →
Search text patterns inside remote files using grep. Returns file paths, line numbers, and matching lines.
Takes no parameters.
Example callreturns →
Show differences between two remote files as a unified diff.
Takes no parameters.
Example callreturns →
Show the last N lines of a remote file (tail). Good for quick log inspection.
Takes no parameters.
Example callreturns →
Compute a hash (md5/sha256/sha512) of a remote file to verify integrity.
Takes no parameters.
Example callreturns →
Query the SSH MCP server internal audit logs. Filter by event type, session, host, or time range.
Takes no parameters.
Example callreturns →
Execute the same command across multiple connected servers simultaneously. Requires multiple active sessionIds.
Takes no parameters.
Example callreturns →
Copy a file from one remote server to another through this MCP server. Requires two active sessionIds.
Takes no parameters.
Example callreturns →
SSH to a target host through an existing session used as a jump/bastion host. Creates a new session on the target.
Takes no parameters.
Example callreturns →
Upload and execute a multi-line script (bash/python/etc.) on the remote server in one step.
Takes no parameters.
Example callreturns →
Create SSH tunnel: forward a local port to a remote host:port through the SSH connection (SSH -L).
Takes no parameters.
Example callreturns →
Create reverse SSH tunnel: forward a remote port back to a local host:port (SSH -R).
Takes no parameters.
Example callreturns →
List all active SSH port forwards and tunnels.
Takes no parameters.
Example callreturns →
Close an active SSH port forward by its forwardId.
Takes no parameters.
Example callreturns →
Manage systemd services on the remote host: start, stop, restart, reload, enable, disable, status, or list all.
Takes no parameters.
Example callreturns →
List, filter, or kill processes on the remote host. Find what is listening on a specific port.
Takes no parameters.
Example callreturns →
View, add, or remove scheduled cron jobs on the remote host.
Takes no parameters.
Example callreturns →
Network diagnostics on the remote host: listening ports, active connections, ping, DNS lookup, routes, interfaces.
Takes no parameters.
Example callreturns →
Get user and group info from the remote host: whoami, list users, user details, group memberships.
Takes no parameters.
Example callreturns →
REQUIRED FIRST STEP: Connect to a remote server via SSH using host, username, and password or key. Must be called before any other ssh_ tool.
Takes no parameters.
Example callreturns →
Close and disconnect an active SSH session by its sessionId.
Takes no parameters.
Example callreturns →
Show all active SSH connections with their host, user, and resource details.
Takes no parameters.
Example callreturns →
Test if an SSH session is alive and measure its round-trip latency.
Takes no parameters.
Example callreturns →
Capture a full system state snapshot: packages, services, ports, processes, cron, env, mounts, users. Use before changes to diff later.
Takes no parameters.
Example callreturns →
Compare two system snapshots to show what changed between them (added/removed packages, services, ports, etc.).
Takes no parameters.
Example callreturns →
Save or manage connection bookmarks. NOT for connecting to servers \u2014 use ssh_connect instead. Only for save/list/delete of saved profiles.
Takes no parameters.
Example callreturns →
List directory contents on the remote server (like ls -la). Shows names, sizes, permissions.
Takes no parameters.
Example callreturns →
Upload a local file to the remote server via SFTP. Validates file size limits.
Takes no parameters.
Example callreturns →
Download a file from the remote server to the local machine via SFTP.
Takes no parameters.
Example callreturns →
Read a remote file text content in-place without downloading. Good for configs and logs.
Takes no parameters.
Example callreturns →
Create or overwrite a remote file with text content. Good for configs and scripts.
Takes no parameters.
Example callreturns →
Delete a file or directory on the remote server. Recursive delete requires explicit opt-in.
Takes no parameters.
Example callreturns →
Get file metadata: size, permissions, owner, timestamps of a remote file or directory.
Takes no parameters.
Example callreturns →
Open an interactive PTY terminal for programs like mysql, python, or top. For simple one-off commands use ssh_exec instead.
Takes no parameters.
Example callreturns →
Type text into an open interactive PTY terminal. Requires shellId from ssh_shell_open.
Takes no parameters.
Example callreturns →
Read output from an open interactive PTY terminal. Requires shellId from ssh_shell_open.
Takes no parameters.
Example callreturns →
Change dimensions of an open PTY terminal window. Requires shellId from ssh_shell_open.
Takes no parameters.
Example callreturns →
Close an interactive PTY terminal. Requires shellId from ssh_shell_open.
Takes no parameters.
Example callreturns →
List open PTY terminals for a specific session.
Takes no parameters.
Example callreturns →
Get remote server system information: OS, CPU, memory, disk, network interfaces, and uptime.
Takes no parameters.
Example callreturns →
Standardmost installed
$15 / month
- 12,000 calls a month, included
- 144 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
Scale
$59 / month
- 100,000 calls a month, included
- 1,200 calls a minute at peak
- Every tool the listing has
- Cancel any time — the unused days are credited
- Runs behind the gateway, so cancelling stops it
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
No call is billed on its own, and this plan carries no monthly call limit. $15 a month covers every tool at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
BTrust score 83 / 100
Release 0.1.1 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score83
Findings15 threat · 12 capability
Capabilitycritical
Coveragesource
Verificationrepo
Surface digest5c0265160035c67b668e98efd6d84f37d385af3285d443ca22fe6411ee57eb93
Score vectorthreat 94 → client 83
| Term | Level | What it prices | Points |
|---|---|---|---|
| −6.3 | |||
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| ssh_connect | no tags | |
| ssh_disconnect | no tags | |
| ssh_list_sessions | no tags | |
| ssh_session_ping | no tags | |
| ssh_exec | code-exec | |
| ssh_sudo_exec | code-exec | |
| ssh_exec_background | code-exec | |
| ssh_exec_poll | code-exec | |
| ssh_exec_poll_list | code-exec | |
| ssh_exec_cancel | code-exec | |
| ssh_shell_open | code-exec | |
| ssh_shell_write | code-exec | |
| ssh_shell_read | code-exec | |
| ssh_shell_resize | code-exec | |
| ssh_shell_close | code-exec | |
| ssh_shell_list | code-exec | |
| ssh_sftp_list | no tags | |
| ssh_sftp_upload | no tags | |
| ssh_sftp_download | untrusted-input | |
| ssh_sftp_read | no tags | |
| ssh_sftp_write | no tags | |
| ssh_sftp_delete | no tags | |
| ssh_sftp_stat | no tags | |
| ssh_port_forward_local | no tags | |
| ssh_port_forward_remote | no tags | |
| ssh_port_forward_list | no tags | |
| ssh_port_forward_remove | no tags | |
| ssh_system_info | no tags | |
| ssh_get_logs | sensitive-source |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
A cross-tool exfiltration chain exists: ssh_sftp_download → ssh_get_logs → ssh_exec.
Supply chain and provenance
Integrityfirst-seen
Surface digest5c0265160035c67b
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 0.1.1 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.1.1
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Simple Ssh in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.