Apply ROT13 cipher (self-inverse: encoding = decoding).
AI agents call rot13 to retrieve information from Crypto Tools MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
ROT13 is a simple, reversible text transformation with no side effects on data storage, system state, or external services. It neither creates/modifies data durably (Write), executes code or external operations (Execute), nor deletes data (Destructive). The tool performs a stateless cryptographic read-like operation: taking input and returning transformed output.
From the tool's definition Tool applies ROT13 cipher transformation. ROT13 is a classical letter substitution cipher that is self-inverse (applying it twice returns the original text).
Attacks that exploit this kind of access
Apply ROT13 cipher (self-inverse: encoding = decoding). It is categorised as a Read tool in the Crypto Tools MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Crypto Tools MCP Server MCP server in PolicyLayer and add a rule for rot13: 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 Crypto Tools MCP Server. Nothing to install.
rot13 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 rot13 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 rot13. 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.
rot13 is provided by the Crypto Tools MCP Server MCP server (marc-shade/crypto-tools-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 →