create_branch_from_head
AI agents use create_branch_from_head to create or update resources in GitBranchMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GitBranchMCP environment.
The tool creates a new branch, which is a reversible data modification operation (branches can be deleted). This qualifies as Write rather than Destructive or other categories. Severity is medium because branch creation has limited blast radius—it creates local organizational state but doesn't delete data or execute arbitrary code.
From the tool's definition Tool name 'create_branch_from_head' indicates creation of a new branch entity. Sibling tools include 'create_branch', 'delete_branch', and 'create_demo_data', establishing a pattern where 'create_*' tools are write operations in this branch management context.
Attacks that exploit this kind of access
create_branch_from_head. It is categorised as a Write tool in the GitBranchMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GitBranch MCP server in PolicyLayer and add a rule for create_branch_from_head: 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 GitBranchMCP. Nothing to install.
create_branch_from_head is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_branch_from_head 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.
Set action: deny in the PolicyLayer policy for create_branch_from_head. 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.
create_branch_from_head is provided by the GitBranch MCP server (lianggaoyuan/gitbranchmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →