create_project_branch · Openl MCP: Risk & Policy

WHAT IT DOES

What create_project_branch does on Openl

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

WHY IT NEEDS A POLICY

Why create_project_branch needs a policy

Creating a project branch is a write operation that adds new data to the system. It is reversible (the branch can be deleted), has limited blast radius when misused by an agent, and does not execute arbitrary code, delete data irreversibly, or move money. Severity is low because branch creation in a rules management system typically has minimal downstream impact without subsequent deployments or modifications.

From the tool's definition Tool name 'create_project_branch' and description 'Create a new branch in a project' indicate creation of a new project branch, a reversible data structure operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_project_branch Rate-limited

create_project_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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Openl, so you can run agents against it safely.

FAQ

Questions about create_project_branch

What does the create_project_branch tool do? +

Create a new branch in a project. It is categorised as a Write tool in the Openl 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_project_branch? +

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

What risk level is create_project_branch? +

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

Can I rate-limit create_project_branch? +

Yes. Add a rate_limit block to the create_project_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_project_branch completely? +

Set action: deny in the PolicyLayer policy for create_project_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_project_branch? +

create_project_branch is provided by the Openl MCP server (openl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.