Get all tokens for the authenticated user
AI agents call pex_list_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 is a Read operation because it retrieves data without modifying or deleting anything. The severity is elevated to 'high' rather than 'low' because tokens are security-critical credentials that could be misused if exposed to an attacker or malicious agent — listing all tokens could facilitate token theft or unauthorized access to the PEX API.
From the tool's definition Tool name is 'pex_list_tokens' and description states 'Get all tokens for the authenticated user' — a retrieval operation with no side effects. However, the tool returns authentication tokens which are sensitive credentials.
Attacks that exploit this kind of access
Get all tokens for the authenticated user. 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_list_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_list_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_list_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_list_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_list_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 →