decrypt_timelock_message
AI agents call decrypt_timelock_message to retrieve information from Shutter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Decryption of an already-expired timelock message is a read operation—it retrieves data without modifying or executing external operations. The Shutter Network's design ensures decryption only succeeds after the specified time has passed, making this a constrained data retrieval. No side effects, data modification, execution, deletion, or financial impact occurs.
From the tool's definition Tool name 'decrypt_timelock_message' and server context indicate retrieval of decrypted message content after timelock expiration.
Attacks that exploit this kind of access
decrypt_timelock_message. It is categorised as a Read tool in the Shutter MCP MCP Server, which means it retrieves data without modifying state.
Register the Shutter MCP server in PolicyLayer and add a rule for decrypt_timelock_message: 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 Shutter MCP. Nothing to install.
decrypt_timelock_message 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_timelock_message 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_timelock_message. 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_timelock_message is provided by the Shutter MCP server (shutter-network/shuttermcp). 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 →