MCP Terminal
Enables management of long-running terminal processes on Linux, allowing AI agents to start, stop, and monitor processes with real-time log capture and search capabilities.
Enables management of long-running terminal processes on macOS, allowing AI agents to start, stop, and monitor processes with real-time log capture and search capabilities.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Terminal start npm run dev for the backend process"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Terminal
MCP server for managing long-running processes and logs. Enables AI agents (Claude Code) to start, stop, and monitor processes with real-time log capture.
Tiếng Việt
Tính năng
Khởi động/Dừng Process - Chạy các process dài và tắt chúng một cách an toàn
Ghi Log thời gian thực - Tất cả stdout/stderr được tự động ghi vào file log
Tìm kiếm Log - Tìm log theo từ khóa hoặc regex
Quản lý Process - Liệt kê các process đang chạy
Log Rotation - Tự động xoay log khi đạt 10MB để tránh đầy ổ đĩa
Tắt an toàn - Tất cả process được dọn dẹp khi server dừng
Cài đặt
Yêu cầu
Node.js >= 18
npm
Các bước
# Clone repository
git clone https://github.com/h004888/mcp_terminal_process.git
cd mcp-terminal
# Cài đặt dependencies
npm install
# Build
npm run buildCấu hình Claude Code
Thêm vào file .claude.json của Claude Code:
Windows: %USERPROFILE%\.claude.json
macOS/Linux: ~/.claude.json
{
"mcpServers": {
"mcp-terminal": {
"command": "node",
"args": ["C:/đường-dẫn/đến/mcp-terminal/dist/index.js"]
}
}
}Cấu hình OpenCode
Thêm vào file opencode.json của OpenCode:
Đường dẫn mặc định: ~/.config/opencode/opencode.json
{
"mcp": {
"mcp-terminal": {
"type": "local",
"command": ["node", "/đường-dẫn/đến/mcp-terminal/dist/index.js"],
"environment": {},
"timeout": 5000
}
}
}Related MCP server: Background Process MCP
English
Features
Start/Stop Processes - Launch long-running processes and terminate them gracefully
Real-time Log Capture - All stdout/stderr automatically written to log files
Log Search - Search logs by keyword or regex
Process Management - List all running processes
Log Rotation - Automatic rotation at 10MB to prevent disk exhaustion
Graceful Shutdown - All processes cleaned up when server stops
Installation
Prerequisites
Node.js >= 18
npm
Steps
# Clone the repository
git clone https://github.com/h004888/mcp_terminal_process.git
cd mcp-terminal
# Install dependencies
npm install
# Build
npm run buildClaude Code Configuration
Add to your Claude Code .claude.json:
Windows: %USERPROFILE%\.claude.json
macOS/Linux: ~/.claude.json
{
"mcpServers": {
"mcp-terminal": {
"command": "node",
"args": ["C:/path/to/mcp-terminal/dist/index.js"]
}
}
}After configuration, restart Claude Code to load the MCP server.
OpenCode Configuration
Add to your OpenCode opencode.json:
Default location: ~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mcp-terminal": {
"type": "local",
"command": ["node", "/path/to/mcp-terminal/dist/index.js"],
"environment": {},
"timeout": 5000,
"enabled": true
}
}
}Example with full path (Windows):
{
"mcp": {
"mcp-terminal": {
"type": "local",
"command": ["node", "C:/Users/ADMIN/Downloads/mcp-terminal/dist/index.js"],
"environment": {},
"timeout": 5000,
"enabled": true
}
}
}Example using npx (if published to npm):
{
"mcp": {
"mcp-terminal": {
"type": "local",
"command": ["npx", "-y", "mcp-terminal"],
"timeout": 5000,
"enabled": true
}
}
}After configuration, restart OpenCode to load the MCP server.
Tools
start_process
Start a long-running process.
{
"id": "backend",
"command": "npm run dev",
"cwd": "C:/path/to/project"
}Parameters:
id(required) - Unique process identifiercommand(required) - Command to executecwd(optional) - Working directory
stop_process
Stop a running process.
{
"id": "backend"
}get_logs
Retrieve logs from a process.
{
"id": "backend",
"lines": 100
}Parameters:
id(required) - Process identifierlines(optional) - Return last N lines only
search_logs
Search logs for a keyword or regex.
{
"id": "backend",
"keyword": "ERROR",
"regex": false
}Parameters:
id(required) - Process identifierkeyword(required) - Search termregex(optional) - Use regex search (default: false)
list_processes
List all running processes.
{}Returns all currently running processes with their IDs, status, command, and log file paths.
Usage Examples
Start a backend server
/mcp start_process {"id": "backend", "command": "npm run dev", "cwd": "C:/my-project"}Check logs
/mcp get_logs {"id": "backend"}Search for errors
/mcp search_logs {"id": "backend", "keyword": "Exception"}List all processes
/mcp list_processes {}Stop a process
/mcp stop_process {"id": "backend"}Architecture
User (Claude Code) → MCP Protocol → MCP Server → Process Manager → logs/*.logComponents:
MCP Server - Handles MCP protocol and exposes tools
Process Manager - Spawns, tracks, and kills child processes
Log Service - File-based log storage with 10MB rotation
Log Files
Logs are stored in the logs/ directory:
logs/{id}.log- Current active loglogs/{id}.1.log- Rotated log (oldest)etc.
Logs are rotated when they exceed 10MB. Maximum 5 rotated files kept per process.
License
MIT
Available Tools
5 toolsget_logsC
Get logs from a process
Inputs: id (required), lines.
list_processesB
List all running processes managed by this MCP server
Inputs: no named parameters.
search_logsC
Search logs for a keyword or regex
Inputs: id (required), keyword (required), regex.
start_processC
Start a long-running process and capture its output to a log file
Inputs: id (required), command (required), cwd.
stop_processC
Stop a running process
Inputs: id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: get_logs retrieves logs, list_processes enumerates processes, search_logs filters logs, start_process initiates processes, and stop_process terminates them. The descriptions reinforce these boundaries, making misselection unlikely.
All tools follow a consistent verb_noun pattern (e.g., get_logs, list_processes, search_logs, start_process, stop_process), using snake_case throughout. This predictability aids agent comprehension and tool selection.
With 5 tools, the set is well-scoped for terminal/process management, covering core operations (list, start, stop processes, and get/search logs). Each tool earns its place without bloat or thinness.
The tools provide strong coverage for process lifecycle (start, stop, list) and log handling (get, search), but minor gaps exist, such as no tool for restarting processes or managing log files (e.g., delete/rotate). Agents can work around this with existing tools.
Maintenance
Related MCP Connectors
Hosted runtime for persistent agent teams, durable workflows, memory, schedules, and goals.
Durable background job execution, async task scheduling, and state persistence for AI agents.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to launch and manage system processes with strict security controls through executable allowlists, resource monitoring, and output capture capabilities.85 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to start, stop, and monitor long-running command-line processes in the background.37 npm11MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to efficiently manage and monitor background processes, with features like process startup, termination, log retrieval, and resource management.14 npm-
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to run commands, capture outputs, and manage background processes with filtering capabilities for debugging and monitoring.-