AI agents call search-documents to retrieve information from BaaS-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a document search tool that retrieves authentication implementation guides based on keyword queries. It performs information retrieval with no side effects, no code execution, no data modification, and no destructive operations. The low severity reflects minimal risk even if an AI agent misuses it—worst case being retrieval of irrelevant documentation.
From the tool's definition Tool description states it 'searches for implementation guides by keyword' (BaaS 인증 시스템의 기능별 구현 가이드를 키워드로 검색합니다). The verb 'search' and the retrieval of documentation/guides indicates query-only behavior with no data modification or execution.
Attacks that exploit this kind of access
BaaS 인증 시스템의 기능별 구현 가이드를 키워드로 검색합니다. ⚠️ 중요: 이 도구를 사용하기 전에 먼저 \. It is categorised as a Read tool in the BaaS-MCP MCP Server, which means it retrieves data without modifying state.
Register the BaaS- MCP server in PolicyLayer and add a rule for search-documents: 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 BaaS-MCP. Nothing to install.
search-documents 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-documents 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-documents. 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-documents is provided by the BaaS- MCP server (mbaas-inc/baas-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 →