modelscope·@aybelatchane/mcp-server-terminal
暂无描述。
MCP server enabling AI agents to interact with terminal applications through structured Terminal State Tree representation. Works with any AI assistant that supports the Model Context Protocol.
npx mcp-server-terminal
Download pre-built binaries from Releases.
git clone https://github.com/aybelatchane/mcp-server-terminal.git
cd mcp-server-terminal
cargo build --release
# Binary: ./target/release/terminal-mcp
claude mcp add terminal -- npx mcp-server-terminal
Add to ~/.claude.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
codex mcp add terminal -- npx mcp-server-terminal
Add to ~/.codex/config.toml:
[mcp_servers.terminal]
command = "npx"
args = ["mcp-server-terminal"]
gemini mcp add terminal npx mcp-server-terminal
VS Code 1.101+ supports MCP. Add to your VS Code settings (settings.json):
{
"mcp.servers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
Add to ~/.cursor/mcp.json or .cursor/mcp.json in your project:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
Add to your Zed settings (Preferences Settings):
{
"context_servers": {
"terminal": {
"command": {
"path": "npx",
"args": ["mcp-server-terminal"]
}
}
}
}
Click MCP Servers icon Configure Advanced MCP Settings, then add:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
Add to your Bedrock agent MCP configuration:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"]
}
}
}
For any MCP-compatible client, configure the server with:
npx["mcp-server-terminal"]Or if using the binary directly:
terminal-mcpAsk your AI agent:
| Tool | Description |
|---|---|
terminal_session_create | Start a terminal session |
terminal_session_list | List active sessions |
terminal_session_close | Close a session |
terminal_session_resize | Resize terminal dimensions |
terminal_snapshot | Capture terminal state with UI elements |
terminal_type | Type text into terminal |
terminal_press_key | Press keys (arrows, F-keys, Ctrl+X) |
terminal_click | Click on detected UI element |
terminal_wait_for | Wait for text, element, or idle state |
terminal_read_output | Read raw terminal output |
By default, sessions spawn a visible terminal window (xterm). For headless operation:
npx mcp-server-terminal --headless
Or in your MCP config:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal", "--headless"]
}
}
}
Visual mode requires X11. Add the DISPLAY environment variable to your MCP config:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"],
"env": {
"DISPLAY": ":0"
}
}
}
}
Set the RUST_LOG environment variable:
{
"mcpServers": {
"terminal": {
"command": "npx",
"args": ["mcp-server-terminal"],
"env": {
"RUST_LOG": "info"
}
}
}
}
Log levels: error, warn, info, debug, trace
Logs go to stderr (stdout is reserved for MCP protocol).
| Platform | Architecture | Status |
|---|---|---|
| Linux | x64, arm64 | Supported |
| macOS | x64, arm64 | Supported |
| Windows | WSL | Supported |
MIT
一个由FastMCP驱动的服务器,用于通过编程方式创建、编辑和渲染PowerPoint(PPTX)演示文稿,具有幻灯片创建、内容插入和PNG渲染等功能。
赋予AI代理在项目背景下使用灵活的MCP工具安全读取和提取PDF文件中的信息(文本、元数据、页数)的能力。
一种模型上下文协议服务器,通过 Graph API 实现与 Microsoft 365 服务(Excel、日历、邮件、OneDrive、Teams 等)的交互,使人工智能助手能够通过自然语言管理 Microsoft 365 资源。
暂无描述。
暂无描述。
暂无描述。