Describe what this API key can do (tools available for its plan).
AI agents call get_plan_info to retrieve information from FixPayment without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves descriptive information about API key capabilities without modifying, executing operations, or moving money. It is purely informational—a read operation that has no side effects. The low severity reflects that exposure merely discloses what permissions exist but does not grant those permissions themselves or enable any destructive actions directly.
From the tool's definition Tool name 'get_plan_info' and description 'Describe what this API key can do (tools available for its plan)' indicate a read-only query that retrieves and displays capability/permission information about an API key.
Attacks that exploit this kind of access
Describe what this API key can do (tools available for its plan). It is categorised as a Read tool in the FixPayment MCP Server, which means it retrieves data without modifying state.
Register the FixPayment MCP server in PolicyLayer and add a rule for get_plan_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 FixPayment. Nothing to install.
get_plan_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 get_plan_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 get_plan_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.
get_plan_info is provided by the FixPayment MCP server (prmail/fixpayment_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 →