AI List Extractor for Any Website MCP Server

Extract a list from any web page on your own LLM key

extract_list_from_website

Read-onlyIdempotent

Extracts structured item lists from public web pages using a URL and plain-language item description, returns one row per item, follows next-page links, and flags missing values.

Instructions

Give web addresses, a plain words description of one item, and your own OpenAI, Anthropic, Gemini, or Groq key. Returns one row per item, follows next page links, and flags values not found on the page. Pages needing JavaScript or refusing plain requests return a free row. With no key it checks up to 3 addresses for free. Pay per event on Apify, plus your provider bill.

Input Schema

Name	Required	Description
`model`	No	Your provider's model name. Defaults: openai gpt-4o-mini, anthropic claude-haiku-4-5-20251001, gemini gemini-2.5-flash, groq llama-3.3-70b-versatile.
`fields`	No	Exact keys each item must carry, for the same columns on every page. Empty lets the model choose. In Clay, wrap a column in a one item list.
`api_key`	No	Your own key. It goes only to the provider you picked and is never stored, logged, or sent to the model. With no key the actor reads up to 3 addresses for free and sends nothing to a model.
`provider`	No	Whose API reads the page, on your key: openai (default), anthropic, gemini, or groq.
`max_items`	No	The run stops after this many items. Default 1000.
`start_urls`	No	Public list pages that answer without a login, for example a careers page or a category page. A page that needs JavaScript or refuses plain requests returns a free row.
`obey_robots`	No	yes (default) or no. A disallowed page returns a free row.
`max_charge_usd`	No	Stops before a page would pass this figure, before your model is called. This limits this actor's charges, not your provider's bill.
`what_to_extract`	No	Plain words, for example: every job: title, company, city, link. Needed when a key is given.
`max_pages_per_url`	No	How many pages to read from each address by following next page links. Default 3, at most 100. Each page your model answers is charged.
`max_chars_per_page`	No	Page text past this length is not sent, which limits your provider bill. Default 40000. The row says when text was cut.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.1Nov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds meaningful operational detail beyond those annotations: pagination via next-page links, free rows for failed/blocked pages, no-key trial behavior, and the billing model split between Apify event charges and the user's provider bill. It does not fully explain what a 'free row' contains or disclose rate limits, so it is strong but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and mostly front-loaded with operational information; every sentence carries relevant behavior or cost context. The opening focuses on inputs before stating the purpose explicitly, and 'free row' is repeated, but there is no major wasted wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 11-parameter tool with no output schema, the description covers output granularity, pagination, failure/free behavior, and key/cost expectations. It reasonably leaves schema-documented details such as fields, max_items, max_charge_usd, robots handling, and model defaults to the input schema. A brief note about output columns would improve completeness, but the definition is operationally sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents all 11 parameters in detail. The description mentions URLs, an extraction description, the provider key, and provider names, but adds little syntax, default, or edge-case meaning beyond the schema. The baseline score of 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a web-list extraction tool: it names the inputs (URLs, an item description, a provider key), the output shape ('one row per item'), pagination, and missing-value flagging. No sibling tools exist, so sibling differentiation is not needed; the purpose is specific enough for an agent to understand immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives useful usage context: provide URLs plus an extraction description and your own provider key, or omit the key to check up to 3 addresses for free. It also explains fallback behavior for JavaScript-heavy or request-refusing pages. It does not state explicit exclusions or alternatives, but no sibling tools are available to compare against.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools

extract_list_from_websiteA