Extract clean, LLM-ready content from up to 5 URLs in one call. POST { urls[], depth? }. Returns the main text content of each page (JS-rendered, boilerplate stripped) plus a list of any URLs that failed. For feeding web pages to an agent without running your own headless browser.
AI agents call search.extract to retrieve information from Mcp 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 data from web pages (reading/querying content) without side effects. It performs content extraction and formatting, which are read-only operations. The tool does not create, modify, delete, or execute code; it simply fetches and cleans existing web content for consumption by an LLM. This is a pure Read operation with minimal risk if misused.
From the tool's definition Tool description states it 'Extract[s] clean, LLM-ready content from up to 5 URLs' and 'Returns the main text content of each page'. The verb 'extract' and 'returns content' indicate retrieval operations.
Attacks that exploit this kind of access
Extract clean, LLM-ready content from up to 5 URLs in one call. POST { urls[], depth? }. Returns the main text content of each page (JS-rendered, boilerplate stripped) plus a list of any URLs that failed. For feeding web pages to an agent without running your own headless browser. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for search.extract: 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 Mcp. Nothing to install.
search.extract 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 search.extract 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 search.extract. 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.
search.extract is provided by the MCP server (@2sio/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 →