AI agents call agloop_get_plan 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 retrieves and queries plan file contents without side effects. It is a read-only operation that merely exposes existing data, fitting the Read category. Severity is low because reading plan files poses minimal risk—the blast radius of misuse is limited to information disclosure of agent planning state, which is typically non-sensitive operational metadata.
From the tool's definition Tool description states it 'Read the current plan' and 'Returns raw file contents' with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Read the current plan (plan.yaml or plan.md). Returns raw file contents. 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_plan: 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_plan 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_plan 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_plan. 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_plan 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 →