# bash_command

Execute a bash command with detailed output and monitoring.

Agent View of the PolicyLayer registry record for `bash_command`. HTML page: https://policylayer.com/tools/a-niranjan-mcp-filesystem/bash-command

## Facts

- Tool: `bash_command`
- Server: MCP Filesystem Server (`a-niranjan/mcp-filesystem`) — https://policylayer.com/tools/a-niranjan-mcp-filesystem.md
- Homepage: https://github.com/A-Niranjan/mcp-filesystem
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "bash_command",
    "arguments": {}
  }
}
```

## Why bash_command is rated High

Bash command execution is a core Execute category risk because it can invoke arbitrary shell operations (loops, pipes, subshells, external tools) with outcomes dependent entirely on the command string argument. Even if constrained to 'predefined directories', bash grants access to environment variables, system utilities, and can perform reads, writes, deletions, or network operations depending on the command.

From the tool's own definition: "Tool name 'bash_command' combined with description 'Execute a bash command' indicates arbitrary command execution."

## Use case

AI agents invoke bash_command to trigger actions in MCP Filesystem Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches MCP Filesystem Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bash_command": {
      "limits": [
        {
          "counter": "bash_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on MCP Filesystem Server (16)

- `bash_execute` — Execute — https://policylayer.com/tools/a-niranjan-mcp-filesystem/bash-execute.md
- `bash_pipe` — Execute — https://policylayer.com/tools/a-niranjan-mcp-filesystem/bash-pipe.md
- `curl_request` — Execute — https://policylayer.com/tools/a-niranjan-mcp-filesystem/curl-request.md
- `execute_command` — Execute — https://policylayer.com/tools/a-niranjan-mcp-filesystem/execute-command.md
- `directory_tree` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/directory-tree.md
- `get_file_info` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/get-file-info.md
- `get_metrics` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/get-metrics.md
- `list_allowed_directories` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/list-allowed-directories.md
- `list_directory` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/list-directory.md
- `read_file` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/read-file.md
- `read_multiple_files` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/read-multiple-files.md
- `search_files` — Read — https://policylayer.com/tools/a-niranjan-mcp-filesystem/search-files.md
- `create_directory` — Write — https://policylayer.com/tools/a-niranjan-mcp-filesystem/create-directory.md
- `edit_file` — Write — https://policylayer.com/tools/a-niranjan-mcp-filesystem/edit-file.md
- `move_file` — Write — https://policylayer.com/tools/a-niranjan-mcp-filesystem/move-file.md
- `write_file` — Write — https://policylayer.com/tools/a-niranjan-mcp-filesystem/write-file.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a-niranjan-mcp-filesystem · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a-niranjan-mcp-filesystem