Medium Risk

create_pull_request

Create a pull request (GitHub) or merge request (GitLab). Auto-detects platform from project. Provide project as slug (owner/repo), full path, or URL. Use extra_options for GitLab-specific options like squash, remove_source_branch, assignee_ids, reviewer_ids, milestone_id.

How to control create_pull_request ↓

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

Medium Risk

An AI agent can call create_pull_request faster than any human can review — one bad instruction and it creates or modifies resources in Preloop by the hundred, each call as confident as the last.

Documented attack patterns abuse exactly the kind of access create_pull_request gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Preloop, and nothing reaches the server without passing your rules. This is the rule we recommend for create_pull_request:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_pull_request": {
      "limits": [
        {
          "counter": "create_pull_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_pull_request stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Preloop — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the create_pull_request tool do? +

Create a pull request (GitHub) or merge request (GitLab). Auto-detects platform from project. Provide project as slug (owner/repo), full path, or URL. Use extra_options for GitLab-specific options like squash, remove_source_branch, assignee_ids, reviewer_ids, milestone_id. It is categorised as a Write tool in the Preloop MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_pull_request? +

Register the Preloop MCP server in PolicyLayer and add a rule for create_pull_request: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Preloop. Nothing to install.

What risk level is create_pull_request? +

create_pull_request is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_pull_request? +

Yes. Add a rate_limit block to the create_pull_request rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block create_pull_request completely? +

Set action: deny in the PolicyLayer policy for create_pull_request. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides create_pull_request? +

create_pull_request is provided by the Preloop MCP server (preloop/preloop). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Preloop tool call.

Deterministic rules across all 15 Preloop tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 Preloop tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.