sshcode-mcp
An MCP server that enables AI assistants to perform development operations on remote servers via SSH, including executing commands, managing files, and browsing directories.
README
sshcode-mcp
SSH Remote AI Development Tool — 通过 SSH 让 AI 在远程计算机上进行开发操作。
基于 MCP (Model Context Protocol) 标准协议，可作为 opencode、Claude Desktop 等 MCP 客户端的工具服务。
功能
| 工具 | 说明 |
|---|---|
execute_command |
在远程服务器执行 shell 命令 |
read_file |
读取远程文件内容 |
write_file |
写入/覆盖远程文件 |
edit_file |
编辑远程文件指定行（按行号） |
list_directory |
列出远程目录内容 |
create_directory |
创建远程目录 |
delete_path |
删除远程文件/目录 |
rename_path |
重命名/移动远程文件/目录 |
file_stat |
获取远程文件元数据 |
search_files |
在远程服务器搜索文件（glob 模式） |
get_system_info |
获取远程系统信息 |
get_pool_stats |
获取连接池/缓存统计 |
快速开始
# 安装依赖
npm install
# 密码认证
node bin/sshcode.js ubuntu@192.168.1.5 -P 123
# 密钥认证
node bin/sshcode.js ubuntu@192.168.1.5 -i ~/.ssh/id_rsa
# 自定义端口
node bin/sshcode.js ubuntu@192.168.1.5 -p 2222 -P 123
环境变量模式（MCP 推荐）
export SSHCODE_HOST=192.168.1.5
export SSHCODE_USER=ubuntu
export SSHCODE_PASSWORD=123
node bin/sshcode.js
配置为 opencode MCP 服务
在 ~/.config/opencode/opencode.jsonc 或项目 .opencode.jsonc 中添加：
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"sshcode": {
"type": "local",
"command": ["node", "/path/to/sshcode_mcp/bin/sshcode.js"],
"environment": {
"SSHCODE_HOST": "192.168.1.5",
"SSHCODE_USER": "ubuntu",
"SSHCODE_PASSWORD": "123",
"SSHCODE_PORT": "22"
},
"timeout": 15000
}
}
}
架构
AI (MCP Client) <-> stdio JSON-RPC <-> sshcode-mcp <-> SSH <-> Remote Server
性能优化
- 连接池: 复用 SSH 连接（最多 5 个），避免重复握手
- 文件缓存: LRU 缓存（最多 50 个文件，TTL 60s）
- 命令超时: 默认 30s，防止长时间卡住
- 并发控制: 最多 10 个并发命令
- 输出截断: 超过 10MB 自动截断
- SFTP 复用: 在同一连接内复用 SFTP 通道
- ssh 压缩: 强制开启压缩减少带宽
配置
# 查看配置
node bin/sshcode.js config
# 修改配置
node bin/sshcode.js config set pool.maxSize 10
node bin/sshcode.js config set command.defaultTimeout 60000
许可证
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.