Schema | mcp-ssh

mcp-ssh

Describes the environment variables required to run the server.

Name	Required	Description	Default
`SSH_PASS`	No	Global password for SSH connections when password authentication is used.
`SSH_LOG_FILE`	No	Log file path.	~/.ssh/mcp-ssh.log
`SSH_LOG_LEVEL`	No	Log level.	INFO
`SSH_KNOWN_HOSTS`	No	Custom trusted host key file path.	system known_hosts
`SSH_PASS_<HOST>`	No	Per-host password. Replace <HOST> with the actual SSH host alias (uppercase, dots/hyphens to underscores). Example: SSH_PASS_MYSERVER
`SSH_REVIEW_MODE`	No	Review mode: off / whitelist / manual / smart	whitelist
`SSH_REVIEW_MANUAL_CHANNEL`	No	Manual confirmation channel: elicit / local / auto	auto
`SSH_REVIEW_WHITELIST_FILE`	No	Whitelist rules file path.	~/.ssh/mcp-ssh-whitelist.conf

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
ssh_execC	在远程主机上执行一条 shell 命令并返回结果。
ssh_list_hostsA	列出 ~/.ssh/config 中配置的主机别名（排除 * 通配项），跨平台适配。
ssh_scanB	扫描局域网网段，发现开放指定端口（默认 SSH 22）的在线主机。
ssh_uploadC	上传本地文件到远程主机。
ssh_downloadC	从远程主机下载文件到本地。
ssh_exec_batchC	批量执行多条命令，支持错误中断。
ssh_list_dirC	列出远程主机指定目录下的文件和子目录。
ssh_stat_fileB	获取远程文件或目录的详细信息。
ssh_mkdirC	在远程主机创建目录。
ssh_removeC	删除远程主机上的文件或目录。
ssh_upload_dirC	上传本地目录到远程主机（递归上传所有文件）。
ssh_download_dirB	从远程主机下载目录到本地（递归下载所有文件）。
ssh_get_review_modeA	获取当前审核模式及状态信息。
ssh_set_review_modeC	动态切换审核模式。可选: off / whitelist / manual / smart。
ssh_get_audit_logsA	查询最近的行为日志（只读，供 AI 分析）。读取 ~/.ssh/mcp-ssh.log（或 SSH_LOG_FILE），按事件聚合为统一行为视图，返回每条含 timestamp/host/username/tool/args/status/duration_ms。支持按 host / tool / since_minutes 过滤；输出受 limit 与大小上限约束。

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/albertm88/mcp-ssh'

If you have feedback or need assistance with the MCP directory API, please join our Discord server