AI agents call get_token to retrieve information from Zentao without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or returns an existing API token rather than creating, modifying, executing, or deleting data. While tokens are sensitive, this tool itself only reads/returns a cached token—it does not modify system state, execute commands, or have irreversible side effects. The risk is low because token exposure depends on downstream misuse by an agent, not on the tool's inherent function.
From the tool's definition Tool name 'get_token' and description 'Get or refresh ZenTao API token (cached)' indicate retrieval of authentication credentials. The verb 'get' and word 'retrieve' are characteristic of Read operations.
Attacks that exploit this kind of access
Get or refresh ZenTao API token (cached). It is categorised as a Read tool in the Zentao MCP Server, which means it retrieves data without modifying state.
Register the Zentao MCP server in PolicyLayer and add a rule for get_token: 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 Zentao. Nothing to install.
get_token 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 get_token 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 get_token. 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.
get_token is provided by the Zentao MCP server (@aipper/zentao-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 →