AI agents call get_file_tree to retrieve information from Astllm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries repository metadata (directory structure, file language info, symbol counts) with no side effects. It is non-destructive, non-executable, and does not modify any data. Even if misused by an AI agent, it merely exposes structural information about the codebase, posing minimal risk.
From the tool's definition get_file_tree returns the file/directory structure with metadata (language, symbol counts) without retrieving file contents.
Attacks that exploit this kind of access
Get the file/directory structure of an indexed repository. Much cheaper than reading files — returns the tree with per-file language and symbol counts. It is categorised as a Read tool in the Astllm MCP Server, which means it retrieves data without modifying state.
Register the Astllm MCP server in PolicyLayer and add a rule for get_file_tree: 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 Astllm. Nothing to install.
get_file_tree 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_file_tree 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_file_tree. 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_file_tree is provided by the Astllm MCP server (tluyben/astllm-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 →