AI agents call get_structure to retrieve information from Doc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural information from an already-analyzed document. It performs a read-only query operation that returns metadata about the document's organization (sections, fields, relationships) without altering the document or triggering side effects. The server context confirms this is a document analysis platform where tools like 'read_section' and 'read_field' also perform read operations.
From the tool's definition Tool name 'get_structure' and description 'get analyzed document structure information' indicate retrieval of metadata about document structure with no modification or deletion.
Attacks that exploit this kind of access
获取已分析文档的结构信息. It is categorised as a Read tool in the Doc MCP Server, which means it retrieves data without modifying state.
Register the Doc MCP server in PolicyLayer and add a rule for get_structure: 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 Doc. Nothing to install.
get_structure 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_structure 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_structure. 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_structure is provided by the Doc MCP server (jiahuidegit/doc-mcp-server). 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 →