Query sigma score bubble information
AI agents call query_sigma_score_bubble_info to retrieve information from AgentGo MCP Service without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves analytics data (sigma scores and bubble information) from the TrustGo platform. The use of 'query' combined with a descriptive phrase indicating information retrieval, with no mention of creation, modification, deletion, or execution capabilities, clearly places this in the Read category.
From the tool's definition Tool name contains 'query' and description states 'Query sigma score bubble information' - indicates data retrieval without modification or side effects.
Attacks that exploit this kind of access
Query sigma score bubble information. It is categorised as a Read tool in the AgentGo MCP Service MCP Server, which means it retrieves data without modifying state.
Register the AgentGo MCP Service MCP server in PolicyLayer and add a rule for query_sigma_score_bubble_info: 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 AgentGo MCP Service. Nothing to install.
query_sigma_score_bubble_info 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 query_sigma_score_bubble_info 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 query_sigma_score_bubble_info. 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.
query_sigma_score_bubble_info is provided by the AgentGo MCP Service MCP server (quan3xin/agentgo-mcp-service). 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 →