ドキュメントをVector検索します。関連するセクションが関連性順で返されます。
AI agents call search 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 searches and retrieves document sections based on natural language input. It returns data without modifying, deleting, or executing anything. This is a pure Read operation with minimal risk—worst case, an agent could search for sensitive information it shouldn't access, but the tool itself does not create, modify, or destroy data.
From the tool's definition Tool description (in Japanese) states: 'ドキュメントをVector検索します。関連するセクションが関連性順で返されます。' which translates to 'Performs vector search on documents. Related sections are returned in order of relevance.' This is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
ドキュメントをVector検索します。関連するセクションが関連性順で返されます。. 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 search: 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.
search 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 search 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 search. 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.
search 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 →