list_causes
AI agents call list_causes to retrieve information from Decoder 3am without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available sleep disruption causes from The Longevity Vault's framework without modifying, executing, or deleting anything. The lack of description lowers confidence slightly, but the tool's name and context within an informational classifier service clearly indicate a read-only operation.
From the tool's definition Tool name 'list_causes' indicates data retrieval with no side effects. Sibling tools ('classify_sleep_cause', 'get_cause_info', 'get_decoder_url') are all Read operations on a diagnostic/informational service.
Attacks that exploit this kind of access
list_causes. It is categorised as a Read tool in the Decoder 3am MCP Server, which means it retrieves data without modifying state.
Register the Decoder 3am MCP server in PolicyLayer and add a rule for list_causes: 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 Decoder 3am. Nothing to install.
list_causes 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 list_causes 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 list_causes. 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.
list_causes is provided by the Decoder 3am MCP server (thelongevityvault/decoder-3am-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_causes is one line of Decoder 3am's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →