switch_branch
AI agents use switch_branch 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 'switch_branch' tool modifies application state by changing which branch is active, enabling subsequent operations on a different branch. This is a Write action (reversible state change) rather than Read (no side effects) or Execute (running arbitrary code).
From the tool's definition Tool name 'switch_branch' combined with sibling tools 'create_branch', 'delete_branch', 'branch_chat' indicates this server manages branch state. Switching a branch changes the active context/state, which is a reversible modification operation.
Attacks that exploit this kind of access
switch_branch. 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 switch_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 GitBranchMCP. Nothing to install.
switch_branch 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 switch_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.
Set action: deny in the PolicyLayer policy for switch_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.
switch_branch 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 →