JWT token\
AI agents call verify_token to retrieve information from MCP JSON Database Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Token verification is a read operation that retrieves and validates token information without creating, modifying, or deleting data. It has no side effects beyond confirming authentication status. The blast radius is minimal—misuse would only affect the current authentication session. Severity is low because verification failures simply deny access rather than exposing sensitive operations.
From the tool's definition Tool name is 'verify_token' with description indicating JWT token verification. The action is to verify/validate a token, which is a read-only operation that checks the validity of authentication credentials without modifying data or triggering side effects.
Attacks that exploit this kind of access
JWT token\. It is categorised as a Read tool in the MCP JSON Database Server MCP Server, which means it retrieves data without modifying state.
Register the MCP JSON Database Server MCP server in PolicyLayer and add a rule for verify_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 MCP JSON Database Server. Nothing to install.
verify_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 verify_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 verify_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.
verify_token is provided by the MCP JSON Database Server MCP server (yusuferenkt/mcp-database). 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 →