Get pending proactive triggers from the memory system. Triggers are generated by memory_think() and represent insights, warnings, or suggestions such as: decaying important memories, consolidation opportunities, detected patterns, or relationship insights. Args: limit: Maximum number of triggers ...
AI agents call trigger_list to retrieve information from Yantrikdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns pending triggers from the memory system. It does not modify, delete, or execute anything. The description explicitly frames it as a 'get' operation returning sorted results, making it a straightforward Read with low blast radius.
From the tool's definition 'Get pending proactive triggers from the memory system' and 'Returns pending triggers sorted by urgency' — purely retrieves/lists data with no side effects
Documented attack patterns abuse exactly the kind of access trigger_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Yantrikdb, and nothing reaches the server without passing your rules. This is the rule we recommend for trigger_list:
{
"version": "1",
"default": "deny",
"tools": {
"trigger_list": {}
}
}trigger_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get pending proactive triggers from the memory system. Triggers are generated by memory_think() and represent insights, warnings, or suggestions such as: decaying important memories, consolidation opportunities, detected patterns, or relationship insights. Args: limit: Maximum number of triggers to return (default 10). Returns pending triggers sorted by urgency. It is categorised as a Read tool in the Yantrikdb MCP Server, which means it retrieves data without modifying state.
Register the Yantrikdb MCP server in PolicyLayer and add a rule for trigger_list: 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 Yantrikdb. Nothing to install.
trigger_list 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 trigger_list 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 trigger_list. 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.
trigger_list is provided by the Yantrikdb MCP server (yantrikos/yantrikdb-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Yantrikdb tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Yantrikdb tools catalogued and risk-classified — across an index of 42,500+ MCP servers.