Work with a remote host over FTP/FTPS/SFTP, SSH, and MySQL.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
An MCP server for working with a single remote host over FTP, FTPS, SFTP, and SSH β the kind of host a typical shared-hosting plan or a plain VPS gives you, not a cloud provider's API. It groups its tools into three capability classes: file transfer (list, upload, download, mkdir, delete), shell execution over SSH, and a MySQL query wrapper that also runs over SSH. File transfer is the only capability enabled by default β shell execution and database access are both opt-in and stay off until you explicitly turn them on. Treat those two as equally dangerous: mysql_query runs arbitrary SQL on a production database and can escape to a shell, so it is not the milder of the pair.
Published to npm and run with npx β there is nothing to clone or build. Requires Node 20 or newer. Works on Windows, macOS and Linux.
On Windows, use the
cmd /cform shown for each client below. Most clients spawncommanddirectly rather than through a shell, andnpxon Windows is a.cmdshim that cannot be executed that way β the server simply fails to start, usually with no useful error. Treat this as the rule on Windows, not an edge case.
.mcp.json in the project rootWindows:
claude_desktop_config.json| OS | Path |
|---|---|
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Same mcpServers shape as Claude Code. Claude Desktop has no project directory, so set MCP_ENV_FILE to an absolute path β see step 2.
.cursor/mcp.json (project) or ~/.cursor/mcp.json (global)Same mcpServers shape as Claude Code.
.vscode/mcp.json (workspace), or MCP: Open User Configuration for globalVS Code uses servers, not mcpServers:
~/.codex/config.toml, or .codex/config.toml in a trusted projectCodex uses TOML with a snake_case mcp_servers table:
Windows:
Or add it from the shell: codex mcp add remote -- npx -y ftp-ssh-mcp@1
Create a .env file in your project root. The server reads it from the working directory, which is the project root for project-scoped clients:
That is enough for the six file tools over FTPS. Keep this file out of version control β add .env and .env.* to .gitignore. Getting credentials out of a tracked config file is the reason the server reads .env at all.
If your client has no project directory (Claude Desktop), or you want several servers against different accounts, point each at its own file instead:
A fuller setup, adding shell execution and database access β both off unless you opt in:
See .env.example for every variable and Configuration below for what each does.
Run it from the directory holding your .env. It resolves configuration, registers tools and prints a one-line summary β without opening a connection β then exits. Use it to confirm the right capabilities came up before wiring the server into a client:
It exits non-zero with a message naming the missing variable if configuration is incomplete. See Troubleshooting.
| Option | Does |
|---|---|
--selftest | Resolve the configuration, print the tools it would register, and exit. Opens no connection. |
-q, --quiet | Drop the informational startup warnings. |
-v, --version | Print the version and exit. |
-h, --help | Print usage and exit. |
--version and --help answer before any configuration is read, so they work on a machine with nothing set up yet. Both print to stdout; everything else the server says goes to stderr, because stdout is the JSON-RPC channel.
--quiet silences the warnings about a missing DB_PASSWORD, an MCP_CAPABILITIES entry that registered no tools, and a relative base directory. It deliberately does not silence the two that say your security posture is weaker than you might assume β an unverified host key, or path confinement switched off. A flag set once in a client's config file is never looked at again, so those stay visible until you fix them, which is the only silence worth having.
A capability's tools are only registered when it is both configured (its required variables are set) and, if MCP_CAPABILITIES restricts the set, named in that list.
| Capability | Tools | Enabled when |
|---|---|---|
files | file_list, file_upload, file_upload_dir, file_download, file_mkdir, file_delete | An FTP or SSH profile is configured. file_delete additionally requires REMOTE_ALLOW_DELETE=true; all writes require REMOTE_READONLY to be unset or false. |
ssh | ssh_exec | An SSH profile is configured with SSH_BASE_DIR set and SSH_ALLOW_EXEC=true. |
mysql | mysql_query | An SSH profile is configured, and DB_USER and DB_NAME are both set. DB_USER must be set explicitly β it does not inherit REMOTE_USER β so the capability cannot switch itself on. Blocked entirely by REMOTE_READONLY=true. DB_PASSWORD is not required β see below. |
The files tools are transport-neutral: they work over whichever transport FILE_TRANSPORT selects (ftp or sftp), and each call can override the transport for that one call if both profiles are configured. mysql_query is a convenience wrapper, not a database driver β it pipes SQL over SSH to the mysql client already installed on the host (mysql --user=... --database=... --table, with the SQL sent on stdin), then parses the CLI's table output. There is no connection pooling and no parameterised-query support. It exists because most shared hosts will not accept a database connection from outside the host itself; if you need a real client-side database integration, use one instead of mysql_query. Enable it with the same caution as ssh_exec, not less β see Security.
Every setting is resolved from environment variables in this order: a profile-specific variable (FTP_* or SSH_*) first, then the shared REMOTE_* fallback, then a built-in default. Two independent profiles exist β FTP and SSH β and you may configure either, both, or neither in isolation (though at least one is required to start).
Variables are normally read from process environment, but the server also loads a .env file from the current working directory before resolving configuration, so credentials can live outside the MCP client's own (often tracked) config file. A real environment variable already set takes precedence over the .env file. Point at a different file with MCP_ENV_FILE β a leading ~ is expanded to your home directory, a relative value is resolved against the working directory, and a set-but-unreadable one fails startup rather than silently falling back to .env and loading different credentials than the ones you named. The .env parser does not support inline comments β KEY=value # note treats everything after = as the value, including # note, so keep comments on their own line.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ftp-ssh-mcp)<a href="https://allmcps.com/mcp/ftp-ssh-mcp"><img src="https://allmcps.com/api/badge/ftp-ssh-mcp?style=directory" alt="Ftp Ssh MCP on AllMCPs" /></a>