Shell CommandSAFE
MCP server for executing shell commands.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server for executing shell commands.
This project is sponsored by ChatWise, an all-in-one LLM chatbot with first-class MCP support.
Usage
Configure manually
# stdio server npx -y shell-command-mcp
JSON config
{
"mcpServers": {
"shell-command": {
"command": "npx",
"args": ["-y", "shell-command-mcp"],
"env": {
"ALLOWED_COMMANDS": "cat,ls,echo"
}
}
}
}Allowed commands
Use ALLOWED_COMMANDS environment variable to explictly allow the commands that this server can run, separate each command by ,. You can use * to allow any command, but this is potentially dangerous.
License
MIT.
22e26add68c0OBSERVED · 2026-10-08Connect
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 shell-command-mcp -- npx -y [email protected]
{
"mcpServers": {
"shell-command-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
execute_command | write | Execute a shell command |
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 | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, args-tokenizer, js-yaml, tinyexec, zod, @types/bun, @types/js-yaml, typescript
Gates applied: no_behavioural_pass, no_license.
22e26add68c0full audit observations/trust-audit/mcp-server/egoist__shell-command-1.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 22e26add68c0 | SAFE | B | 89 | first audit |
Questions
What is the Shell Command MCP server?
MCP server for executing shell commands.
What tools does Shell Command expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Shell Command 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.
What credentials does Shell Command need?
No credential environment variables were found in its source, so it appears to need none.
How does Shell Command run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as shell-command-mcp at 0.0.1.
How current is this page?
The grade is for one exact copy of the source (22e26add68c0), read on 2026-10-08. The repository is watched and re-audited when it changes.