Decrypt AES-256-GCM encrypted data. Input must include nonce and tag.
AI agents call decrypt_data to retrieve information from Tenzro Ledger MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Decryption is fundamentally a read operation: it converts encrypted data to readable form without side effects or state changes. However, severity is elevated to 'medium' rather than 'low' because successful decryption of sensitive financial or identity data (implied by the server's wallet, payments, identity functions) could expose confidential information if decryption keys are compromised or an agent decrypts…
From the tool's definition Tool decrypts data via 'Decrypt AES-256-GCM encrypted data' but does not modify, delete, or execute code/commands—it only retrieves plaintext from ciphertext.
Attacks that exploit this kind of access
Decrypt AES-256-GCM encrypted data. Input must include nonce and tag. It is categorised as a Read tool in the Tenzro Ledger MCP MCP Server, which means it retrieves data without modifying state.
Register the Tenzro Ledger MCP server in PolicyLayer and add a rule for decrypt_data: 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 Tenzro Ledger MCP. Nothing to install.
decrypt_data 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 decrypt_data 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 decrypt_data. 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.
decrypt_data is provided by the Tenzro Ledger MCP server (https://canton-mcp.tenzro.network/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 →