Get the QIT configuration directory path.
AI agents call get_qit_dir to retrieve information from QIT 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 metadata about the QIT configuration directory location. It has no side effects, does not modify state, does not execute commands, and does not delete or move data. It is purely informational, comparable to querying a system property. The blast radius if misused is minimal—an attacker gains only knowledge of a directory path, not access to its contents or ability to modify them.
From the tool's definition Tool name 'get_qit_dir' and description 'Get the QIT configuration directory path' indicate a retrieval operation that returns a filesystem path without modifying or executing anything.
Attacks that exploit this kind of access
Get the QIT configuration directory path. It is categorised as a Read tool in the QIT MCP Server MCP Server, which means it retrieves data without modifying state.
Register the QIT MCP Server MCP server in PolicyLayer and add a rule for get_qit_dir: 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 QIT MCP Server. Nothing to install.
get_qit_dir 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_qit_dir 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_qit_dir. 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_qit_dir is provided by the QIT MCP Server MCP server (woocommerce/qit-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 →