AI agents call get-document-by-id 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 tool retrieves specific document content based on an ID parameter. It performs a query operation with no side effects, no data modification, and no execution of external commands. The most severe risk is exposure of potentially sensitive authentication documentation, but the operation itself is read-only.
From the tool's definition Tool name 'get-document-by-id' and description indicate retrieval of document content by ID from a BaaS authentication system. The verb '조회합니다' (query/retrieve) explicitly signals a read-only operation with no modification or deletion.
Attacks that exploit this kind of access
문서 ID로 특정 BaaS 인증 시스템 문서의 전체 내용을 조회합니다. ⚠️ 중요: 이 문서만으로 구현하지 말고, \. 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 get-document-by-id: 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.
get-document-by-id 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-document-by-id 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-document-by-id. 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-document-by-id 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 →