set_model_provider · GitBranch MCP: Risk & Policy

WHAT IT DOES

What set_model_provider does on GitBranchMCP

AI agents use set_model_provider 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 set_model_provider needs a policy

This tool creates or modifies configuration data (API provider and model settings) without deleting or executing arbitrary code. It's a reversible write operation that changes system settings. Severity is medium because misconfiguration could affect tool behavior downstream, but the direct blast radius is limited to configuration state rather than data deletion or financial impact.

From the tool's definition Tool description indicates 'set' operation (设置 means 'set/configure' in Chinese) for model API provider and model configuration. This modifies application configuration state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_model_provider Rate-limited

set_model_provider 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": {
    "set_model_provider": {
      "limits": [
        {
          "counter": "set_model_provider_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 set_model_provider

What does the set_model_provider tool do? +

设置可选模型 API provider 和 model。. 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 set_model_provider? +

Register the GitBranch MCP server in PolicyLayer and add a rule for set_model_provider: 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 set_model_provider? +

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

Can I rate-limit set_model_provider? +

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

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

set_model_provider 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.