# shellcheck

Runs ShellCheck (shell script linter) and returns structured diagnostics (file, line, column, rule, severity, message).

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

## Facts

- Tool: `shellcheck`
- Server: Lint (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-lint.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": "shellcheck",
    "arguments": {}
  }
}
```

## Why shellcheck is rated High

This tool executes an external program (ShellCheck) against files. While its stated purpose is linting, it 'runs' an external process on arbitrary input files. An AI agent could potentially abuse this to process unintended files or trigger unexpected behavior. The execution of external processes is inherently Execute category, with high severity due to the broad file access implied.

From the tool's own definition: "Runs ShellCheck (shell script linter)"

## Use case

AI agents invoke shellcheck to trigger actions in Lint. 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 Lint:

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

## Other tools on Lint (201)

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