STEP 4: RAG Tool. Extracts and cleans text from the current page
AI agents call extract_weather_data_rag to retrieve information from Israel Weather AI Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and processes text content from a webpage that has already been loaded by Playwright. It performs no side effects, creates no data, executes no code, and makes no state changes. It is a classic Read operation within a RAG (retrieval-augmented generation) pipeline.
From the tool's definition Tool description states it 'Extracts and cleans text from the current page' — a data retrieval operation with no modification, deletion, or command execution. The verb 'extract' and 'clean' indicate read-only parsing of already-loaded DOM content.
Attacks that exploit this kind of access
STEP 4: RAG Tool. Extracts and cleans text from the current page. It is categorised as a Read tool in the Israel Weather AI Agent MCP Server, which means it retrieves data without modifying state.
Register the Israel Weather AI Agent MCP server in PolicyLayer and add a rule for extract_weather_data_rag: 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 Israel Weather AI Agent. Nothing to install.
extract_weather_data_rag 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 extract_weather_data_rag 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 extract_weather_data_rag. 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.
extract_weather_data_rag is provided by the Israel Weather AI Agent MCP server (rivka414/mcp). 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 →