branch_chat · GitBranch MCP: Risk & Policy

WHAT IT DOES

What branch_chat does on GitBranchMCP

AI agents use branch_chat 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.

WHY IT NEEDS A POLICY

Why branch_chat needs a policy

The tool writes new conversation data to a branch context. While reversible (branches can be deleted via delete_branch), it permanently records AI-generated content in the branch structure. This is clearly Write rather than Read (it doesn't just retrieve), not Execute (no external commands/code execution), not Destructive (the operation is reversible), and not Financial.

From the tool's definition Tool enables creation and modification of conversation state within a specified branch (隔离模型对话 = 'isolated model conversation').

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

branch_chat Rate-limited

branch_chat 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": {
    "branch_chat": {
      "limits": [
        {
          "counter": "branch_chat_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 GitBranchMCP, so you can run agents against it safely.

FAQ

Questions about branch_chat

What does the branch_chat tool do? +

在指定分支中进行隔离模型对话。. 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.

How do I enforce a policy on branch_chat? +

Register the GitBranch MCP server in PolicyLayer and add a rule for branch_chat: 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.

What risk level is branch_chat? +

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

Can I rate-limit branch_chat? +

Yes. Add a rate_limit block to the branch_chat 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_chat completely? +

Set action: deny in the PolicyLayer policy for branch_chat. 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_chat? +

branch_chat 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.