# shell

Makes packages available in the environment and optionally runs a command. Returns stdout, stderr, exit code, and duration.

Agent View of the PolicyLayer registry record for `shell`. HTML page: https://policylayer.com/tools/io-github-dave-london-build/shell

## Facts

- Tool: `shell`
- Server: Build (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-build.md
- Homepage: https://github.com/Dave-London/pare
- 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": "shell",
    "arguments": {}
  }
}
```

## Why shell is rated High

The tool explicitly runs commands and returns stdout/stderr/exit code, indicating arbitrary shell command execution. This is a critical risk because an AI agent could misuse it to run any command on the host system, including destructive or exfiltrating operations. Rated Execute (not Destructive) because the primary categorization is command execution; destructive potential depends on what command is run.

From the tool's own definition: "'optionally runs a command. Returns stdout, stderr, exit code, and duration' — this tool executes arbitrary shell commands in the environment"

## Use case

AI agents invoke shell to trigger actions in Build. 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 Build:

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

## Other tools on Build (201)

- `branch` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/branch.md
- `clean` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/clean.md
- `remove` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/remove.md
- `reset` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/reset.md
- `secret-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/secret-delete.md
- `tag` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/tag.md
- `variable-delete` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/variable-delete.md
- `workspace` — Destructive — https://policylayer.com/tools/io-github-dave-london-build/workspace.md
- `add` — Execute — https://policylayer.com/tools/io-github-dave-london-build/add.md
- `add-package` — Execute — https://policylayer.com/tools/io-github-dave-london-build/add-package.md
- `ansible-galaxy` — Execute — https://policylayer.com/tools/io-github-dave-london-build/ansible-galaxy.md
- `ansible-playbook` — Execute — https://policylayer.com/tools/io-github-dave-london-build/ansible-playbook.md
- `api` — Execute — https://policylayer.com/tools/io-github-dave-london-build/api.md
- `apply` — Execute — https://policylayer.com/tools/io-github-dave-london-build/apply.md
- `audit` — Execute — https://policylayer.com/tools/io-github-dave-london-build/audit.md
- `bazel` — Execute — https://policylayer.com/tools/io-github-dave-london-build/bazel.md
- `biome-check` — Execute — https://policylayer.com/tools/io-github-dave-london-build/biome-check.md
- `bisect` — Execute — https://policylayer.com/tools/io-github-dave-london-build/bisect.md
- `black` — Execute — https://policylayer.com/tools/io-github-dave-london-build/black.md
- `build` — Execute — https://policylayer.com/tools/io-github-dave-london-build/build.md
- `bundle-exec` — Execute — https://policylayer.com/tools/io-github-dave-london-build/bundle-exec.md
- `bundle-install` — Execute — https://policylayer.com/tools/io-github-dave-london-build/bundle-install.md
- `check` — Execute — https://policylayer.com/tools/io-github-dave-london-build/check.md
- `cherry-pick` — Execute — https://policylayer.com/tools/io-github-dave-london-build/cherry-pick.md
- `clippy` — Execute — https://policylayer.com/tools/io-github-dave-london-build/clippy.md
- `cmake` — Execute — https://policylayer.com/tools/io-github-dave-london-build/cmake.md
- `compose-build` — Execute — https://policylayer.com/tools/io-github-dave-london-build/compose-build.md
- `compose-down` — Execute — https://policylayer.com/tools/io-github-dave-london-build/compose-down.md
- `compose-up` — Execute — https://policylayer.com/tools/io-github-dave-london-build/compose-up.md
- `conda` — Execute — https://policylayer.com/tools/io-github-dave-london-build/conda.md
- …and 171 more: https://policylayer.com/tools/io-github-dave-london-build.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=io-github-dave-london-build · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-dave-london-build