当用户询问 GitBranchMCP 总览、当前上下文、有哪些分支、最近保存了什么时调用。
AI agents call get_context_overview 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.
The tool retrieves and presents information about the state of branches and context within the GitBranchMCP system. It performs read-only queries to answer informational questions about the system's current state. No data is created, modified, deleted, or irreversibly changed. This is a classic Read category tool.
From the tool's definition Tool description indicates it is called when users ask about 'GitBranchMCP overview, current context, what branches exist, what was recently saved' — all query/retrieval operations with no modification or side effects.
Attacks that exploit this kind of access
当用户询问 GitBranchMCP 总览、当前上下文、有哪些分支、最近保存了什么时调用。. 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_context_overview: 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_context_overview 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_context_overview 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_context_overview. 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_context_overview 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 →