AI agents call describe_scopes 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 retrieves and displays information about API scopes—it does not modify, execute code, delete data, or move money. It is purely informational, helping users understand what permissions exist. The blast radius of misuse is minimal; an attacker could only learn what scopes are available, not exploit them without valid credentials. Classified as Read with low severity.
From the tool's definition Tool name 'describe_scopes' and description indicate it 'returns all permission scopes and descriptions' (반환합니다) for a DataGSM API Key. This is a query/lookup operation retrieving metadata about available permissions.
Attacks that exploit this kind of access
DataGSM API Key의 모든 권한 Scope와 설명을 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 describe_scopes: 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.
describe_scopes 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 describe_scopes 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 describe_scopes. 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.
describe_scopes 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 →