Analyze entire directories using Gemini CLI with @ syntax
AI agents call gemini_analyze_directories to retrieve information from Gemini MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code/directory contents for inspection purposes. There is no evidence it modifies files, executes code, deletes data, or performs financial operations. The @ syntax mentioned is a querying mechanism in Gemini CLI for reading file context.
From the tool's definition Tool performs 'codebase analysis' and 'directory analysis' without any indication of data modification, deletion, or execution capabilities. The description specifies 'analysis' and 'overviews' of existing code, which are read-only operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Analyze entire directories using Gemini CLI with @ syntax. It is categorised as a Read tool in the Gemini MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Gemini MCP Server MCP server in PolicyLayer and add a rule for gemini_analyze_directories: 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 Gemini MCP Server. Nothing to install.
gemini_analyze_directories 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 gemini_analyze_directories 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 gemini_analyze_directories. 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.
gemini_analyze_directories is provided by the Gemini MCP Server MCP server (juparave/gemini-mcp). 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 →