semantic_search_memory와 동일 스코프로 검색 후 tiktoken 예산 내 마크다운 블록을 만듭니다.
AI agents call inject_relevant_memories to retrieve information from Infinite Context Keeper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though inject_relevant_memories only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
semantic_search_memory와 동일 스코프로 검색 후 tiktoken 예산 내 마크다운 블록을 만듭니다. It is categorised as a Read tool in the Infinite Context Keeper MCP Server, which means it retrieves data without modifying state.
Register the Infinite Context Keeper MCP server in PolicyLayer and add a rule for inject_relevant_memories: 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.
inject_relevant_memories 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 inject_relevant_memories 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 inject_relevant_memories. 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.
inject_relevant_memories 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.