Get a list of basic token details for the authenticated user and app
AI agents call pex_get_auth_tokens to retrieve information from PEX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists token details—a read-only operation with no side effects. However, severity is elevated to 'medium' rather than 'low' because token details, even basic metadata, could be sensitive information that an AI agent might inadvertently expose or misuse if obtained through prompt injection or manipulation.
From the tool's definition Tool name 'pex_get_auth_tokens' with description 'Get a list of basic token details for the authenticated user and app' indicates retrieval of authentication token metadata without modification.
Attacks that exploit this kind of access
Get a list of basic token details for the authenticated user and app. It is categorised as a Read tool in the PEX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PEX MCP Server MCP server in PolicyLayer and add a rule for pex_get_auth_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 PEX MCP Server. Nothing to install.
pex_get_auth_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 pex_get_auth_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 pex_get_auth_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.
pex_get_auth_tokens is provided by the PEX MCP Server MCP server (pexcard/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 →