summarization_start_ratio(기본 75%) 이상일 때만 실행하도록 context_percentage 또는 used_tokens+max_tokens로 검증합니다.
AI agents invoke trigger_compaction to trigger actions in Infinite Context Keeper. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
trigger_compaction triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
summarization_start_ratio(기본 75%) 이상일 때만 실행하도록 context_percentage 또는 used_tokens+max_tokens로 검증합니다. It is categorised as a Execute tool in the Infinite Context Keeper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Infinite Context Keeper MCP server in PolicyLayer and add a rule for trigger_compaction: 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 Infinite Context Keeper. Nothing to install.
trigger_compaction is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the trigger_compaction 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_compaction. 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_compaction is provided by the Infinite Context Keeper MCP server (sujkh85/infinite-context-keeper-node). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.