AI agents call decrypt_local_value to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs cryptographic decryption of existing local data, which is fundamentally a read operation. It accesses encrypted information but does not create, modify, delete, or execute code. The operation is reversible and has no destructive or external side effects.
From the tool's definition Tool name contains 'decrypt' and description states 'Decrypt a local encrypted JSON value' — it retrieves and decrypts data without modifying or deleting it. No side effects mentioned.
Attacks that exploit this kind of access
Decrypt a local encrypted JSON value with the configured profile key. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for decrypt_local_value: 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 Todos. Nothing to install.
decrypt_local_value 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_local_value 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_local_value. 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_local_value is provided by the Todos MCP server (@hasna/todos). 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 →