AI agents call search_docs to retrieve information from Datagsm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries existing documentation. It has no side effects—it does not create, modify, delete, execute code, or move money. It is a straightforward Read operation that carries minimal risk if misused by an AI agent, as it can only expose information that already exists in public documentation.
From the tool's definition Tool name is 'search_docs' and description states it searches DataGSM official documentation and returns page contents related to keywords. The verb 'search' and 'find' (찾아) and 'return contents' (반환) indicate retrieval of existing data with no modification.
Attacks that exploit this kind of access
DataGSM 공식 문서에서 키워드와 관련된 페이지를 찾아 내용을 반환합니다. It is categorised as a Read tool in the Datagsm MCP Server, which means it retrieves data without modifying state.
Register the Datagsm MCP server in PolicyLayer and add a rule for search_docs: 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 Datagsm. Nothing to install.
search_docs 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_docs 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_docs. 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_docs is provided by the Datagsm MCP server (snowykte0426/datagsm-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 →