pr-create

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

SERVERHttp SOURCE@paretools/http

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-http/pr-create.md

WHAT IT DOES

What pr-create does on Http

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

RISK

Why pr-create is rated Medium

Creating a pull request is a write operation that generates new data structures in a version control system. While reversible (PRs can be closed), it modifies repository state and could be misused to inject malicious code, spam, or disrupt workflows. The high severity reflects potential for abuse in automated workflows where an AI agent might create many unwanted PRs or attempt to merge unvetted code.

From the tool's definition Tool name 'pr-create' and description states it 'Creates a new pull request' with return of PR number and URL. This is a create operation that modifies repository state by introducing a new PR.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pr-create safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Http, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pr-create, this is the rule to start with:

pr-create Rate-limited

pr-create 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pr-create": {
      "limits": [
        {
          "counter": "pr-create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Http, apply this rule, and every pr-create call is checked against it from then on.

FAQ

Questions about pr-create

What does the pr-create tool do? +

Creates a new pull request. Returns structured data with PR number and URL. It is categorised as a Write tool in the Http MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on pr-create? +

Register the Http MCP server in PolicyLayer and add a rule for pr-create: 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 Http. Nothing to install.

What risk level is pr-create? +

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

Can I rate-limit pr-create? +

Yes. Add a rate_limit block to the pr-create 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 pr-create completely? +

Set action: deny in the PolicyLayer policy for pr-create. 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 pr-create? +

pr-create is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Http, and thousands of servers like it.

This server

All 202 Http tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →