MCP Shell Server

Thực thi các lệnh shell an toàn từ các trợ lý AI và các máy khách MCP khác, với các cài đặt bảo mật có thể cấu hình.

Tài liệu

mcp-shell

Trust Score glama

MCP server that runs shell commands. Your LLM gets a tool; you get control over what runs and how.

Built on mark3labs/mcp-go. Written in Go.


Run it

Docker (easiest):

docker run -it --rm -v /tmp/mcp-workspace:/tmp/mcp-workspace sonirico/mcp-shell:latest

From source:

git clone https://github.com/sonirico/mcp-shell && cd mcp-shell
make install
mcp-shell

Configure it

Secure mode is the default. With no config file, mcp-shell boots in secure mode restricted to a narrow allowlist of read-only utilities (ls, cat, grep, find, head, tail, ...). You only need a config file to widen or change that policy. To run fully unrestricted you must opt in explicitly:

MCP_SHELL_ALLOW_UNSAFE=true mcp-shell   # disables all validation - do not use in production

To customize the policy, point to a YAML config:

export MCP_SHELL_SEC_CONFIG_FILE=/path/to/security.yaml
mcp-shell

Secure mode (recommended) — no shell interpretation, executable allowlist only:

security:
  enabled: true
  use_shell_execution: false
  allowed_executables:
    - ls
    - cat
    - grep
    - find
    - echo
  # WARNING: never add shell/language interpreters (bash, sh, python, perl,
  # ruby, node) or alias-capable tools (git) here - the interpreter executes
  # whatever it is handed, bypassing secure mode entirely. mcp-shell warns at
  # startup if it finds one.
  blocked_patterns:          # optional: restrict args on allowed commands
    - '(^|\s)remote\s+(-v|--verbose)(\s|$)'
  max_execution_time: 30s
  max_output_size: 1048576
  working_directory: /tmp/mcp-workspace
  audit_log: true

Legacy mode — shell execution, allowlist/blocklist by command string (vulnerable to injection if not careful):

security:
  enabled: true
  use_shell_execution: true
  allowed_commands: [ls, cat, grep, echo]
  blocked_patterns: ['rm\s+-rf', 'sudo\s+']
  max_execution_time: 30s
  audit_log: true

Wire it up

Claude Desktop — add to your MCP config:

{
  "mcpServers": {
    "shell": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "sonirico/mcp-shell:latest"],
      "env": { "MCP_SHELL_LOG_LEVEL": "info" }
    }
  }
}

For custom config, mount the file and set the env:

{
  "command": "docker",
  "args": ["run", "--rm", "-i", "-v", "/path/to/security.yaml:/etc/mcp-shell/security.yaml", "-e", "MCP_SHELL_SEC_CONFIG_FILE=/etc/mcp-shell/security.yaml", "sonirico/mcp-shell:latest"]
}

Tool API

ParameterTypeDescription
commandstringShell command to run (required)
base64booleanEncode stdout/stderr as base64 (default: false)

Response includes status, exit_code, stdout, stderr, command, execution_time, and optional security_info.


Environment variables

VariableDescription
MCP_SHELL_SEC_CONFIG_FILEPath to security YAML (overrides built-in secure defaults)
MCP_SHELL_ALLOW_UNSAFESet true to disable all validation and run unrestricted (opt-in)
MCP_SHELL_SERVER_NAMEServer name (default: "mcp-shell 🐚")
MCP_SHELL_LOG_LEVELdebug, info, warn, error, fatal
MCP_SHELL_LOG_FORMATjson, console
MCP_SHELL_LOG_OUTPUTstdout, stderr, file

Development

make install dev-tools   # deps + goimports, golines
make fmt test lint
make docker-build       # build image locally
make release            # binary + docker image

Security

  • Default: Secure mode, restricted to a narrow allowlist of read-only utilities. No interpreters.
  • Secure mode (use_shell_execution: false): the command is parsed into a shell AST and only a single, fully-literal simple command is accepted (no pipes, lists, substitution, redirection or globs); its executable must be on the allowlist. Interpreters (bash/sh/python) are hard-denied even if allowlisted, and per-tool policies strip escape hatches (git -c, find -exec, tar --checkpoint-action). This is an early-reject layer, not a sandbox.
  • Unrestricted: Only via MCP_SHELL_ALLOW_UNSAFE=true. Full access; fine for local dev, dangerous otherwise.
  • Docker: Runs as non-root, Alpine-based. Use it in production. Best paired with an OS sandbox (read-only FS, dropped caps) as defense-in-depth.

Contributing

Fork, branch, make fmt test, open a PR.