Terminal ControllerSAFE
A Model Context Protocol (MCP) server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface.
[](https://smithery.ai/server/@GongRzhe/terminal-controller-mcp)
Features
- Command Execution: Run terminal commands with timeout controls and comprehensive output capture
- Directory Management: Navigate and list directory contents with intuitive formatting
- Security Measures: Built-in safeguards against dangerous commands and operations
- Command History: Track and display recent command executions
- Cross-Platform Support: Works on both Windows and UNIX-based systems
- File Operations: Read, write, update, insert, and delete file content with row-level precision
Installation
Installing via Smithery
To install Terminal Controller for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @GongRzhe/terminal-controller-mcp --client claude
Prerequisites
- Python 3.11+
- An MCP-compatible client (such as Claude Desktop)
- UV/UVX installed (optional, for UVX method)
Method 1: PyPI Installation (Recommended)
Install the package directly from PyPI:
pip install terminal-controller
Or if you prefer to use UV:
uv pip install terminal-controller
Method 2: From Source
If you prefer to install from source:
- Clone this repository:
git clone https://github.com/GongRzhe/terminal-controller-mcp.git cd terminal-controller-mcp
- Run the setup script:
python setup_mcp.py
Client Configuration
Claude Desktop
There are two ways to configure Claude Desktop to use Terminal Controller:
Option 1: Using UVX (Recommended)
Add
49aa192985b2OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add terminal-controller -- uvx terminal-controller
{
"mcpServers": {
"terminal-controller": {
"command": "uvx",
"args": [
"terminal-controller"
]
}
}
}Exposed tools (10)
5 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
change_directory | read | |
delete_file_content | destructive | |
execute_command | write | |
get_command_history | read | |
get_current_directory | read | |
insert_file_content | write | |
list_directory | read | |
read_file | read | |
update_file_content | write | |
write_file | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
delete_file_content
mcp, httpx
Gates applied: no_behavioural_pass.
49aa192985b2full audit observations/trust-audit/mcp-server/gongrzhe__terminal-controller.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 49aa192985b2 | SAFE | B | 89 | first audit |
Questions
What is the Terminal Controller MCP server?
A Model Context Protocol (MCP) server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface.
What tools does Terminal Controller expose?
10 in total: 5 read-only, 4 that write, and 1 that can delete or overwrite (delete_file_content). Every one is listed on this page with its risk.
Is Terminal Controller safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Terminal Controller need?
No credential environment variables were found in its source, so it appears to need none.
How does Terminal Controller run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as terminal-controller.
How current is this page?
The grade is for one exact copy of the source (49aa192985b2), read on 2026-10-07. The repository is watched and re-audited when it changes.