List the account's API tokens (secrets are never returned).
AI agents call list_api_tokens to retrieve information from QR Forge 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 information about existing API tokens without creating, modifying, or deleting them. It is purely informational. However, API tokens are security-sensitive objects; listing them could help an attacker identify which integrations or services are connected to an account, raising the severity to medium rather than low.
From the tool's definition The tool description explicitly states it 'List[s] the account's API tokens', which is a retrieval operation. The clarification that 'secrets are never returned' confirms this is a read-only query with no modification capability.
Attacks that exploit this kind of access
List the account's API tokens (secrets are never returned). It is categorised as a Read tool in the QR Forge MCP server MCP Server, which means it retrieves data without modifying state.
Register the QR Forge MCP server MCP server in PolicyLayer and add a rule for list_api_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 QR Forge MCP server. Nothing to install.
list_api_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 list_api_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 list_api_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.
list_api_tokens is provided by the QR Forge MCP server MCP server (jkolarov/qrforge-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 →