# pr-create

Creates a new pull request. Returns structured data with PR number and URL.

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

## Facts

- Tool: `pr-create`
- Server: Lint (`Dave-London/Pare`) — https://policylayer.com/tools/io-github-dave-london-lint.md
- Homepage: https://github.com/Dave-London/pare
- Risk category: Write (Medium 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": "pr-create",
    "arguments": {}
  }
}
```

## Why pr-create is rated Medium

The tool creates a new pull request, which is a reversible write operation. A PR can be closed or deleted, unlike a merge or delete operation. However, it has moderate severity because an AI agent misusing this could create unwanted PRs that disrupt workflows, require cleanup, or expose incomplete work.

From the tool's own definition: "Tool description states 'Creates a new pull request' - a write operation that creates new data (PR) with side effects on a repository system."

## Use case

AI agents use pr-create to create or update resources in Lint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lint environment.

## 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": {
    "pr-create": {
      "limits": [
        {
          "counter": "pr-create_rate",
          "window": "minute",
          "max": 30,
          "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