create_branch

THE RISK

Medium Risk

Why create_branch needs a policy

Creating a branch is a Write operation because it creates new repository metadata that can be undone (branches can be deleted). It is not Destructive since branch creation is reversible. While it interacts with an external system (GitHub), it does not execute arbitrary code or trigger deployments.

From the tool's definition Tool creates a new branch in a GitHub repository, which is a reversible modification to repository state. The description explicitly states 'Create a new branch' indicating it writes/creates data in the Git system.

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

POLICY

How to control create_branch

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_branch": {
      "limits": [
        {
          "counter": "create_branch_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_branch 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.

Create a free account and register Claude TypeScript MCP Servers — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude TypeScript MCP Servers tools

Destructive delete_file Delete a file. This operation cannot be undone. Only works within allowed directories. Destructive delete_release Delete a release Execute puppeteer_clear_input Clear an input field Execute batch_operations Execute multiple file operations efficiently. Supports transactional mode (rollback on err Execute puppeteer_emulate_device Emulate a specific device Execute puppeteer_evaluate Execute JavaScript in the browser console Execute puppeteer_evaluate_in_frame Execute JavaScript in a specific frame Execute puppeteer_navigate Navigate to a URL

All 84 Claude TypeScript MCP Servers tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about create_branch

What does the create_branch tool do? +

Create a new branch in a GitHub repository. It is categorised as a Write tool in the Claude TypeScript MCP Servers 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_branch? +

Register the Claude TypeScript MCP Servers MCP server in PolicyLayer and add a rule for create_branch: 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 Claude TypeScript MCP Servers. Nothing to install.

What risk level is create_branch? +

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

Can I rate-limit create_branch? +

Yes. Add a rate_limit block to the create_branch 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_branch completely? +

Set action: deny in the PolicyLayer policy for create_branch. 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_branch? +

create_branch is provided by the Claude TypeScript MCP Servers MCP server (ukkz/claude-ts-mcps). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude TypeScript MCP Servers tool call.

Start from Claude TypeScript MCP Servers, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →