How do I configure the MCP SSH/SFTP 服务器?
Copy `servers.json.example` to a new file named `servers.json`, then fill in the server details (host, port, username, password). The file is already in `.gitignore` to prevent accidental commits.
@naya-cat-1
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A collection of SSH and SFTP servers implementing the Model Context Protocol (MCP). The SSH server enables remote command execution, while the SFTP server provides file transfer capabilities such as listing directories, uploading, and downloading files. It is intended for developers and operators who need programmatic remote server management and file operations via an MCP-compatible interface.
Copy servers.json.example to servers.json, then edit the file with your server credentials (host, port, username, password). The MCP host (e.g., an AI assistant) can then call the provided tools: execute_ssh_command for SSH commands, and list_directory, upload_file, download_file for SFTP operations. Each tool requires the server connection parameters and the operation-specific path/command.
Copy `servers.json.example` to a new file named `servers.json`, then fill in the server details (host, port, username, password). The file is already in `.gitignore` to prevent accidental commits.
The current implementation uses password authentication. The README recommends using private key authentication instead for better security.
Both SSH and SFTP servers implement connection timeout handling. The SFTP server additionally features automatic retry on failure. All errors produce detailed messages, and resources (connections) are automatically cleaned up after each operation.
Passwords are only kept in memory temporarily and never persisted to disk. Each operation automatically disconnects, and the connection has a timeout mechanism. The configuration file (`servers.json`) is ignored by version control.
SSH: `execute_ssh_command` (requires host, port, username, password, command). SFTP: `list_directory`, `upload_file`, `download_file` (each require host, port, username, password, and the relevant remote/local path).
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and
Comments