AI agents call user_tokens to retrieve information from Semaphore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing API tokens belonging to the authenticated user. It performs a read-only query with no side effects, data modification, code execution, or deletion. The blast radius is minimal—an agent could learn token identifiers but cannot create, delete, or modify tokens through this tool alone, and token values are typically redacted in listings.
From the tool's definition Tool name 'user_tokens' combined with description 'List API tokens for the current user' indicates a query/retrieval operation with no modification capability.
Attacks that exploit this kind of access
List API tokens for the current user. It is categorised as a Read tool in the Semaphore MCP Server, which means it retrieves data without modifying state.
Register the Semaphore MCP server in PolicyLayer and add a rule for user_tokens: 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 Semaphore. Nothing to install.
user_tokens 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 user_tokens 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 user_tokens. 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.
user_tokens is provided by the Semaphore MCP server (vitexsoftware/semaphore-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 →