Third to use: Process large result sets in streaming batches for comprehensive analysis. Use when you need to analyze many results systematically.
AI agents call stream_batches to retrieve information from National Library of Israel Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval and analysis tool that accesses existing data in batches without modifying, deleting, or executing operations. It fits the Read category as it retrieves and queries data with no side effects.
From the tool's definition Tool processes and streams result sets from the National Library of Israel's digital archive for analysis.
Attacks that exploit this kind of access
Third to use: Process large result sets in streaming batches for comprehensive analysis. Use when you need to analyze many results systematically. It is categorised as a Read tool in the National Library of Israel Search MCP MCP Server, which means it retrieves data without modifying state.
Register the National Library of Israel Search MCP server in PolicyLayer and add a rule for stream_batches: 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 National Library of Israel Search MCP. Nothing to install.
stream_batches 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 stream_batches 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 stream_batches. 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.
stream_batches is provided by the National Library of Israel Search MCP server (mula2812/nli_ai_search). 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 →