AI agents call jwt_decode to retrieve information from Devutils without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and decodes existing JWT data, displaying its header and payload. No data is created, modified, or deleted. However, severity is medium because JWTs often contain sensitive claims (user identity, roles, permissions), and decoding them without signature verification could expose sensitive information if tokens are inadvertently shared with or logged by the tool.
From the tool's definition Decode a JWT (JSON Web Token) and display its header and payload without verifying the signature
Attacks that exploit this kind of access
Decode a JWT (JSON Web Token) and display its header and payload without verifying the signature. Useful for debugging and inspecting tokens. It is categorised as a Read tool in the Devutils MCP Server, which means it retrieves data without modifying state.
Register the Devutils MCP server in PolicyLayer and add a rule for jwt_decode: 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 Devutils. Nothing to install.
jwt_decode 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 jwt_decode 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 jwt_decode. 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.
jwt_decode is provided by the Devutils MCP server (paladini/devutils-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 →