AI agents call decrypt_metadata_fields 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 accesses encrypted data by decrypting it, which is fundamentally a read operation. It retrieves sensitive information but does not create, modify, delete, or execute external operations. The decryption itself does not alter the encrypted metadata—it only reveals its contents.
From the tool's definition Tool is named 'decrypt_metadata_fields' and described as decrypting sensitive fields in a metadata object. Decryption is a read operation that retrieves plaintext from encrypted data without modifying or destroying the underlying encrypted state.
Attacks that exploit this kind of access
Decrypt sensitive fields in a metadata object. 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_metadata_fields: 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_metadata_fields 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_metadata_fields 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_metadata_fields. 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_metadata_fields 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 →