create_pull_request

Create a new pull request in a GitHub repository.

SERVERGitHub SOURCEoci:ghcr.io/github/github-mcp-server:1.3.0

Medium RISK CLASS

Category Write

Parameters 80 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity verified Pull the record →

This record as markdown: /tools/github/create-pull-request.md

WHAT IT DOES

What create_pull_request does on GitHub

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

Parameter	Type	Required	Description
`base`	string	—	Branch to merge into
`body`	string	—	PR description
`head`	string	—	Branch containing changes
`repo`	string	—	Repository name
`draft`	boolean	—	Create as draft PR
`owner`	string	—	Repository owner
`title`	string	—	PR title
`maintainer_can_modify`	boolean	—	Allow maintainer edits

Parameters from the server's own tool schema.

RISK

Why create_pull_request is rated Medium

This tool creates a new pull request, which is a reversible write operation. A pull request can be closed, deleted, or discarded without permanent data loss. While it can trigger workflows and have side effects, the primary action is creating a reviewable change proposal, not executing arbitrary code or deleting data.

From the tool's definition Tool name is 'create_pull_request' and description states 'Create a new pull request in a GitHub repository.' The verb 'create' and the action of introducing a new pull request into a repository indicates data creation.

Risk signalsAccepts raw HTML/template content (body)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs create_pull_request safely

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

create_pull_request Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_pull_request": {
      "limits": [
        {
          "counter": "create_pull_request_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 GitHub, apply this rule, and every create_pull_request call is checked against it from then on.

FAQ

Questions about create_pull_request

What does the create_pull_request tool do? +

Create a new pull request in a GitHub repository. It is categorised as a Write tool in the GitHub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does create_pull_request accept? +

create_pull_request accepts 8 parameters: base, body, head, repo, draft, owner, title, maintainer_can_modify. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on create_pull_request? +

Register the GitHub 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 GitHub. 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 GitHub MCP server (oci:ghcr.io/github/github-mcp-server:1.3.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on GitHub, and thousands of servers like it.

This server

All 86 GitHub 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 →