AI agents call td_get_root to retrieve information from Td without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool returns metadata about the project structure (root path). It performs no modifications, deletions, or execution of code. Callers may use this path as input to other tools, but td_get_root itself only reads and returns information. Misuse risk is minimal—an agent might learn a path it shouldn't have, but cannot manipulate state or execute operations through this tool alone.
From the tool's definition Tool description states it 'Get[s] the actual project root path' — a query operation that retrieves information without side effects.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get the actual project root path. Call this FIRST before using any other tool that requires a path. It is categorised as a Read tool in the Td MCP Server, which means it retrieves data without modifying state.
Register the Td MCP server in PolicyLayer and add a rule for td_get_root: 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 Td. Nothing to install.
td_get_root 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 td_get_root 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 td_get_root. 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.
td_get_root is provided by the Td MCP server (tai5863/td-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 →