# 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-github/shellcheck

## Facts

- Tool: `shellcheck`
- Server: Github (`@paretools/github`) — https://policylayer.com/tools/io-github-dave-london-github.md
- Install: `npx -y @paretools/github`
- 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

The tool executes an external program (ShellCheck) against shell scripts. While it is read-only in intent (linting/static analysis), it actively runs an external process whose behavior depends on the input arguments. This falls under Execute. Misuse could involve pointing it at arbitrary files on the filesystem, but blast radius is limited since it only reads and reports diagnostics without modifying anything.

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

## Use case

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

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

## Other tools on Github (201)

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