AI agents call agloop_list_agents to retrieve information from Agloop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple directory listing operation to retrieve agent metadata. It has no side effects, does not execute code, and does not modify any state. The blast radius of misuse is minimal—an agent could discover available agents but cannot interact with them or cause harm through listing alone. This is a classic Read operation.
From the tool's definition Tool name 'agloop_list_agents' and description 'List all available agent names in .github/agents/' indicate a read-only operation that retrieves and enumerates agent names from a directory. No modification, execution, or deletion occurs.
Attacks that exploit this kind of access
List all available agent names in .github/agents/. It is categorised as a Read tool in the Agloop MCP Server, which means it retrieves data without modifying state.
Register the Agloop MCP server in PolicyLayer and add a rule for agloop_list_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 Agloop. Nothing to install.
agloop_list_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 agloop_list_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 agloop_list_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.
agloop_list_agents is provided by the Agloop MCP server (zebbern/agloop-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 →