List key lifecycle entries for an agent. Requires TETHER_API_KEY.
AI agents call list_agent_keys to retrieve information from Tether Name 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 key lifecycle information for an agent without modifying, deleting, or executing any operations. It is purely informational in nature. The requirement for TETHER_API_KEY is an authentication control, not an indication of higher severity. The blast radius is limited to information disclosure of key metadata.
From the tool's definition Tool name includes 'list' which is a read operation; description states 'List key lifecycle entries' with no modification, deletion, or execution capabilities mentioned.
Attacks that exploit this kind of access
List key lifecycle entries for an agent. Requires TETHER_API_KEY. It is categorised as a Read tool in the Tether Name MCP Server, which means it retrieves data without modifying state.
Register the Tether Name MCP server in PolicyLayer and add a rule for list_agent_keys: 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 Tether Name. Nothing to install.
list_agent_keys 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 list_agent_keys 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 list_agent_keys. 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.
list_agent_keys is provided by the Tether Name MCP server (tether-name-mcp-server). 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 →