About Shell Proxy
Shell Proxy is a command execution proxy for AI agents that runs commands between an agent and a terminal, returning structured output while reducing interference from ANSI codes, shell startup noise, and encoding issues. It supports multiple shells and buffered or line-by-line streaming output.
Key features
- 01Strip ANSI control sequences
- 02Bypass shell initialization files
- 03Detect or select a shell
- 04Structured JSON command results
- 05Stream output line by line
- 06Truncate output or write it to a file
Use cases
- 01Provide agents with readable terminal output
- 02Monitor long-running commands as they stream
- 03Run commands in different shells
- 04Save command results to a file
MCP support
Its stdio MCP server exposes run_command and run_command_stream tools for executing commands and returning either complete JSON results or line-by-line output.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEshellproxy
shellproxy is a clean command execution proxy for AI agents, solving the "terminal blindness" problem — garbage characters, ANSI escape codes, shell init noise, and encoding issues that make AI agents unable to read terminal output.
It sits between AI agents and terminals, executing commands in a clean, controlled environment and returning structured JSON output.
Features
- ANSI stripping — removes all color codes, cursor movements, and control sequences
- Shell init bypass — runs
bash --norc --noprofile, PowerShell with-NoProfile, etc. - Auto shell detection — prefers WSL bash on Windows, falls back to cmd; bash/sh on Unix
- Structured JSON output —
exit_code,stdout,stderr,duration_ms,shell,truncated - Streaming mode — line-by-line output for long-running commands
- File output — write results to a file in addition to stdout
- MCP server — exposes
run_commandandrun_command_streamas MCP tools - Configurable — env vars, config file
~/.shellproxy.json, or CLI flags
Installation
Unix (Linux, macOS, WSL)
curl -sSL https://raw.githubusercontent.com/aliforever/shellproxy/main/install.sh | sh
Windows (PowerShell)
irm https://raw.githubusercontent.com/aliforever/shellproxy/main/install.ps1 | iex
From source
git clone https://github.com/aliforever/shellproxy
cd shellproxy
go build -o shellproxy .
Usage
Run a command (buffered)
shellproxy run "echo hello world"
Output:
{
"exit_code": 0,
"stdout": "hello world\n",
"stderr": "",
"duration_ms": 12,
"shell": "wsl",
"truncated": false
}
Run with plain text output
shellproxy run --output text "ls -la"
Stream output line by line
shellproxy run --stream "npm install"
Output:
[stdout] added 342 packages in 4.2s
[stdout] found 0 vulnerabilities
--- exit_code: 0 | duration: 4213ms | shell: wsl ---
Write result to file
shellproxy run --file /tmp/result.json "go build ./..."
Specify a shell explicitly
shellproxy run --shell cmd "dir"
shellproxy run --shell bash "cat /etc/os-release"
shellproxy run --shell pwsh "Get-Date"
Inject environment variables
shellproxy run --env "NODE_ENV=production" --env "PORT=8080" "node server.js"
Set a timeout
shellproxy run --timeout 30 "long-running-command"
Truncate large output
shellproxy run --truncate 4096 "cat large-file.log"
MCP Server Mode
Start shellproxy as an MCP server over stdio:
shellproxy serve
AI Client Configuration
Add shellproxy to your AI client's MCP config:
{
"mcpServers": {
"shellproxy": {
"command": "shellproxy",
"args": ["serve"],
"env": {
"SHELLPROXY_SHELL": "auto",
"SHELLPROXY_TIMEOUT": "60"
}
}
}
}
Available MCP Tools
| Tool | Description |
|---|---|
run_command | Execute a command and return complete JSON result |
run_command_stream | Execute a command and return output line-by-line |
run_command parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
command | string | ✓ | Shell command to execute |
shell | string | auto, cmd, bash, wsl, pwsh, sh | |
cwd | string | Working directory | |
timeout_seconds | number | Timeout (0 = no limit) | |
env | object | Extra env vars as {"KEY": "VALUE"} | |
truncate_bytes | number | Max output size in bytes |
Configuration
shellproxy can be configured via environment variables or a JSON config file.
Config file: ~/.shellproxy.json
{
"shell": "auto",
"timeout_seconds": 60,
"strip_ansi": true,
"output_mode": "buffered",
"output_file": "",
"truncate_bytes": 0
}
Environment variables
| Variable | Default | Description |
|---|---|---|
SHELLPROXY_SHELL | auto | Shell to use |
SHELLPROXY_TIMEOUT | 60 | Timeout in seconds |
SHELLPROXY_STRIP_ANSI | true | Strip ANSI codes (0/false to disable) |
SHELLPROXY_OUTPUT_MODE | buffered | buffered, stream, or file |
SHELLPROXY_OUTPUT_FILE | File path for file output mode | |
SHELLPROXY_TRUNCATE_BYTES | 0 | Truncate output at N bytes |
SHELLPROXY_CONFIG | ~/.shellproxy.json | Override config file path |
Global Flags
Flags:
--shell string Shell to use: auto, cmd, bash, wsl, pwsh, sh (default "auto")
--timeout int Command timeout in seconds 0 = no timeout (default 60)
--strip-ansi Strip ANSI escape codes from output (default true)
-h, --help help for shellproxy
Building from Source
# Build for current platform
make build
# Build for all platforms
make build-all
# Run tests
make test
# Run specific test suites
make test-strip # ANSI stripping tests
make test-detect # Shell detection tests
make test-exec # Integration exec tests
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.