Critical Risk →

branch

Lists, creates, renames, or deletes branches. Returns structured branch data. Pass

How to control branch ↓

What branch does on Github

AI agents call branch to permanently remove resources in Github — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why branch needs a policy

The tool explicitly supports deleting branches, which is an irreversible destructive operation. Since the most severe applicable category must be chosen, and branch deletion cannot be undone (especially on remote repositories), this classifies as Destructive. The blast radius is high as deleting branches can cause loss of work and disrupt CI/CD pipelines.

From the tool's definition Lists, creates, renames, or deletes branches

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

How to control branch

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

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "branch"
  ]
}

branch disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Github — 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.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about branch

What does the branch tool do? +

Lists, creates, renames, or deletes branches. Returns structured branch data. Pass. It is categorised as a Destructive tool in the Github MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on branch? +

Register the Github MCP server in PolicyLayer and add a rule for 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 Github. Nothing to install.

What risk level is branch? +

branch is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit branch? +

Yes. Add a rate_limit block to the 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 branch completely? +

Set action: deny in the PolicyLayer policy for 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 branch? +

branch is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Github tool call.

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

Free to start. No card required.

202 Github tools catalogued and risk-classified — across an index of 43,000+ 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.