查看可选模型 API 配置状态。
AI agents call get_model_status to retrieve information from GitBranchMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries or retrieves the status of model API configurations. It performs a read-only operation with no side effects, no data creation/modification, no code execution, and no destructive actions. The blast radius is minimal—an AI agent obtaining configuration status information poses negligible security risk in a local-first branch notes application context.
From the tool's definition Tool name 'get_model_status' and description '查看可选模型 API 配置状态' (view optional model API configuration status) indicates retrieval of configuration or status information without modification.
Attacks that exploit this kind of access
查看可选模型 API 配置状态。. It is categorised as a Read tool in the GitBranchMCP MCP Server, which means it retrieves data without modifying state.
Register the GitBranch MCP server in PolicyLayer and add a rule for get_model_status: 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.
get_model_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_model_status 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 get_model_status. 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.
get_model_status 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 →