# bundle-exec

Executes a command in the context of the Gemfile bundle using

Agent View of the PolicyLayer registry record for `bundle-exec`. HTML page: https://policylayer.com/tools/io-github-dave-london-pare-test/bundle-exec

## Facts

- Tool: `bundle-exec`
- Server: Test (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-pare-test.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": "bundle-exec",
    "arguments": {}
  }
}
```

## Why bundle-exec is rated High

The tool explicitly executes arbitrary commands within the Gemfile bundle context. This is a command execution tool — the blast radius is high since an AI agent could run any command available in the bundle environment, potentially affecting the filesystem, processes, or external systems.

From the tool's own definition: "'Executes a command in the context of the Gemfile bundle'"

## Use case

AI agents invoke bundle-exec to trigger actions in Test. 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 Test:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bundle-exec": {
      "limits": [
        {
          "counter": "bundle-exec_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Test (201)

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