AI agents call agloop_get_agent_info 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.
The tool retrieves agent metadata and prompt configuration from a definition file. It is purely informational—no state is changed, no commands are executed, and no data is deleted or created. This is a straightforward read operation with minimal risk unless the agent prompt itself contains sensitive credentials (which would be a separate concern about what is stored, not about the tool's function).
From the tool's definition Tool name and description: 'Read the definition file (.agent.md) for a specific agent. Returns the full agent prompt including frontmatter.' This is a retrieval operation that reads and returns data without modification or side effects.
Attacks that exploit this kind of access
Read the definition file (.agent.md) for a specific agent. Returns the full agent prompt including frontmatter. 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_get_agent_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 Agloop. Nothing to install.
agloop_get_agent_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 agloop_get_agent_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 agloop_get_agent_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.
agloop_get_agent_info 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 →