Get normalized project tree
AI agents call get_project_tree to retrieve information from Coding MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns the project's directory structure (a 'tree' view). It performs no writes, deletions, command execution, or financial operations. The function is purely informational, making it a standard Read category tool with low severity since viewing project structure poses minimal risk even in an adversarial scenario.
From the tool's definition Tool name 'get_project_tree' and description 'Get normalized project tree' indicate a retrieval operation that returns file structure information without modifying data.
Attacks that exploit this kind of access
Get normalized project tree. It is categorised as a Read tool in the Coding MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Coding MCP Server MCP server in PolicyLayer and add a rule for get_project_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 Coding MCP Server. Nothing to install.
get_project_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_project_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_project_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_project_tree is provided by the Coding MCP Server MCP server (kieutrongthien/coding-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 →