文書の目次構造をトークン数付きで一覧表示します。文書の全体像把握や記述量バランスの確認に使えます。
AI agents call get_outline to retrieve information from Search Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays the outline structure and token counts of a document. It performs no mutations, executions, deletions, or financial operations. It is a straightforward Read operation with minimal blast radius—an AI agent misusing it could at worst enumerate document structure unnecessarily, but cannot alter data or trigger side effects.
From the tool's definition Tool description (translated) states: 'Display document outline structure with token counts. Can be used for grasping the overall picture of documents and confirming the balance of written content.' This is a retrieval operation that queries document…
Attacks that exploit this kind of access
文書の目次構造をトークン数付きで一覧表示します。文書の全体像把握や記述量バランスの確認に使えます。. It is categorised as a Read tool in the Search Docs MCP Server, which means it retrieves data without modifying state.
Register the Search Docs MCP server in PolicyLayer and add a rule for get_outline: 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 Search Docs. Nothing to install.
get_outline 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_outline 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_outline. 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_outline is provided by the Search Docs MCP server (otolab/search-docs). 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 →