AI agents call gt_agents to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters agent data for querying purposes. It has no side effects, does not execute operations, and does not modify, delete, or create resources. It is a straightforward read operation that returns information about agents matching specified criteria.
From the tool's definition Tool name and description indicate a list operation: 'List Gas Town agents with optional role and rig filters'. The verb 'List' and the filter parameters (role, rig) suggest a query that retrieves information without modifying state.
Attacks that exploit this kind of access
List Gas Town agents with optional role and rig filters. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for gt_agents: 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 Ruflo. Nothing to install.
gt_agents 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 gt_agents 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 gt_agents. 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.
gt_agents is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
gt_agents is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →