Batch scrape webpages with Firecrawl

Batch scrape webpages with Firecrawl. Supply body.urls. A field-level output specification is not published in this Tool's current contract. The native run result is the authority for returned data. This draft does not promise unobserved fields, complete coverage or a guaranteed match. Current ceiling: 3.000000 credits. Use one Toolmu account and shared balance across available Tools. Pay per use; no required subscription. The credit ceiling is separate from monetary values returned in the data.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Batch scrape webpages with Firecrawl. Complete this task using the exact Toolmu Tool below. Reuse a working Toolmu connection; if needed, follow https://toolmu.com/SKILL.md. Read its current contract, ask for missing required input, verify availability, current price, balance and budget, then execute within the user authorization and explain the returned result. Do not create a replacement for UNKNOWN or an unconfirmed run.
Tool: batch-scrape-webpages-with-firecrawl-firecrawl
Supply body.urls.

Task:
Paste [one or more webpage links anyone can open] to collect them together, up to 500 pages at a time. This tool works on links you already have; it does not find pages for you.

Paste into your connected AI's conversation.

Connection guide

Up to 3 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Firecrawl

Batch scrape webpages with Firecrawl

You receive

Batch scrape webpages with Firecrawl. A field-level output specification is not published in this Tool's current contract. The native run result is the authority for returned data. This draft does not promise unobserved fields, complete coverage or a guaranteed match.

Start with your task

Paste [one or more webpage links anyone can open] to collect them together, up to 500 pages at a time. This tool works on links you already have; it does not find pages for you.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
body`body`	`object`	Required	Scrape up to 500 URLs as one job Required fields `urls`
json`body.json`	`boolean`	Optional	Extract structured JSON from the page with an LLM — costs five times a plain scrape (see the price card's JSON tier).
urls`body.urls`	`array`	Required	The URLs to scrape (1-500). Minimum items `1` Maximum items `500`
[]`body.urls[]`	`string`	—	Format `uri`
proxy`body.proxy`	`string`	Optional	'auto' (default) retries with enhanced anti-bot proxies when the plain fetch is blocked — no extra charge either way. Options `basic, enhanced, auto`
maxAge`body.maxAge`	`integer`	Optional	Cache-reuse window in ms — a fresh-enough cached copy returns much faster. 0 forces a live fetch. Minimum `0` Maximum `604800000`
mobile`body.mobile`	`boolean`	Optional
formats`body.formats`	`array`	Optional	Output formats (default markdown). LLM extraction is the separate 'json' option. Minimum items `1` Maximum items `6`
[]`body.formats[]`	`string`	—	Options `markdown, html, rawHtml, links, images, summary`
timeout`body.timeout`	`integer`	Optional	Per-page deadline in ms; time queued for a browser counts too. Minimum `1000` Maximum `120000`
waitFor`body.waitFor`	`integer`	Optional	Extra ms to wait after load for JavaScript-heavy pages. Minimum `0` Maximum `30000`
blockAds`body.blockAds`	`boolean`	Optional
location`body.location`	`object`	Optional
country`body.location.country`	`string`	Optional	ISO 3166-1 alpha-2 country code to emulate (e.g. 'US'). Minimum length `2` Maximum length `2`
languages`body.location.languages`	`array`	Optional	Preferred languages, best-effort (e.g. ['en']). Maximum items `5`
[]`body.location.languages[]`	`string`	—	Minimum length `2` Maximum length `10`
jsonPrompt`body.jsonPrompt`	`string`	Optional	What to extract from the page (with json: true). Minimum length `1` Maximum length `2000`
jsonSchema`body.jsonSchema`	`object`	Optional	JSON Schema the extracted object must conform to (with json: true).
excludeTags`body.excludeTags`	`array`	Optional	Maximum items `50`
[]`body.excludeTags[]`	`string`	—	Minimum length `1`
includeTags`body.includeTags`	`array`	Optional	Maximum items `50`
[]`body.includeTags[]`	`string`	—	Minimum length `1`
onlyMainContent`body.onlyMainContent`	`boolean`	Optional	Strip headers, navs, and footers (default true).
ignoreInvalidURLs`body.ignoreInvalidURLs`	`boolean`	Optional	Skip malformed entries instead of failing the batch.
removeBase64Images`body.removeBase64Images`	`boolean`	Optional

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "urls"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "json": {
          "type": "boolean",
          "description": "Extract structured JSON from the page with an LLM — costs five times a plain scrape (see the price card's JSON tier)."
        },
        "urls": {
          "type": "array",
          "items": {
            "type": "string",
            "format": "uri"
          },
          "maxItems": 500,
          "minItems": 1,
          "description": "The URLs to scrape (1-500)."
        },
        "proxy": {
          "enum": [
            "basic",
            "enhanced",
            "auto"
          ],
          "type": "string",
          "description": "'auto' (default) retries with enhanced anti-bot proxies when the plain fetch is blocked — no extra charge either way."
        },
        "maxAge": {
          "type": "integer",
          "maximum": 604800000,
          "minimum": 0,
          "description": "Cache-reuse window in ms — a fresh-enough cached copy returns much faster. 0 forces a live fetch."
        },
        "mobile": {
          "type": "boolean"
        },
        "formats": {
          "type": "array",
          "items": {
            "enum": [
              "markdown",
              "html",
              "rawHtml",
              "links",
              "images",
              "summary"
            ],
            "type": "string"
          },
          "maxItems": 6,
          "minItems": 1,
          "description": "Output formats (default markdown). LLM extraction is the separate 'json' option."
        },
        "timeout": {
          "type": "integer",
          "maximum": 120000,
          "minimum": 1000,
          "description": "Per-page deadline in ms; time queued for a browser counts too."
        },
        "waitFor": {
          "type": "integer",
          "maximum": 30000,
          "minimum": 0,
          "description": "Extra ms to wait after load for JavaScript-heavy pages."
        },
        "blockAds": {
          "type": "boolean"
        },
        "location": {
          "type": "object",
          "properties": {
            "country": {
              "type": "string",
              "maxLength": 2,
              "minLength": 2,
              "description": "ISO 3166-1 alpha-2 country code to emulate (e.g. 'US')."
            },
            "languages": {
              "type": "array",
              "items": {
                "type": "string",
                "maxLength": 10,
                "minLength": 2
              },
              "maxItems": 5,
              "description": "Preferred languages, best-effort (e.g. ['en'])."
            }
          },
          "additionalProperties": false
        },
        "jsonPrompt": {
          "type": "string",
          "maxLength": 2000,
          "minLength": 1,
          "description": "What to extract from the page (with json: true)."
        },
        "jsonSchema": {
          "type": "object",
          "description": "JSON Schema the extracted object must conform to (with json: true).",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "excludeTags": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "maxItems": 50
        },
        "includeTags": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "maxItems": 50
        },
        "onlyMainContent": {
          "type": "boolean",
          "description": "Strip headers, navs, and footers (default true)."
        },
        "ignoreInvalidURLs": {
          "type": "boolean",
          "description": "Skip malformed entries instead of failing the batch."
        },
        "removeBase64Images": {
          "type": "boolean"
        }
      },
      "description": "Scrape up to 500 URLs as one job",
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

What this Tool does

Batch scrape webpages with Firecrawl. Supply body.urls.

Inputs and conditions

body — object; Required. Scrape up to 500 URLs as one job

body.json — boolean; Optional. Extract structured JSON from the page with an LLM — costs five times a plain scrape (see the price card's JSON tier).

body.urls — array; Required. The URLs to scrape (1-500). {"minItems":1,"maxItems":500}

body.proxy — string; Optional. 'auto' (default) retries with enhanced anti-bot proxies when the plain fetch is blocked — no extra charge either way. {"enum":["basic","enhanced","auto"]}

body.maxAge — integer; Optional. Cache-reuse window in ms — a fresh-enough cached copy returns much faster. 0 forces a live fetch. {"minimum":0,"maximum":604800000}

body.mobile — boolean; Optional.

body.formats — array; Optional. Output formats (default markdown). LLM extraction is the separate 'json' option. {"minItems":1,"maxItems":6}

body.timeout — integer; Optional. Per-page deadline in ms; time queued for a browser counts too. {"minimum":1000,"maximum":120000}

body.waitFor — integer; Optional. Extra ms to wait after load for JavaScript-heavy pages. {"minimum":0,"maximum":30000}

body.blockAds — boolean; Optional.

body.location — object; Optional.

body.location.country — string; Optional. ISO 3166-1 alpha-2 country code to emulate (e.g. 'US'). {"minLength":2,"maxLength":2}

body.location.languages — array; Optional. Preferred languages, best-effort (e.g. ['en']). {"maxItems":5}

body.jsonPrompt — string; Optional. What to extract from the page (with json: true). {"minLength":1,"maxLength":2000}

body.jsonSchema — object; Optional. JSON Schema the extracted object must conform to (with json: true).

body.excludeTags — array; Optional. {"maxItems":50}

body.includeTags — array; Optional. {"maxItems":50}

body.onlyMainContent — boolean; Optional. Strip headers, navs, and footers (default true).

body.ignoreInvalidURLs — boolean; Optional. Skip malformed entries instead of failing the batch.

body.removeBase64Images — boolean; Optional.

Returned information

A field-level output specification is not published in this Tool's current contract. The native run result is the authority for returned data. This draft does not promise unobserved fields, complete coverage or a guaranteed match.

Price and account

Current published execution ceiling: 3.000000 credits. Use one Toolmu account and shared balance across available Tools. Pay per use; no required subscription. The credit ceiling is separate from monetary values returned in the data.

Limits and freshness

Results depend on the supplied input and the provider's coverage at execution time. Missing records, null fields or a limited result set do not prove that an entity does not exist. A saved Example is historical; viewing it does not execute this Tool.

Source and verification

Contract and price verified through Toolmu MCP on 2026-10-02T02:35:33.570Z (UTC). Toolmu Tool: batch-scrape-webpages-with-firecrawl-firecrawl.

https://docs.firecrawl.dev/api-reference/introduction

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Batch scrape webpages with Firecrawl. Supply body.urls.

Batch scrape webpages with Firecrawl

Batch scrape webpages with Firecrawl

You receive

Start with your task

Inputs & outputs

Input schema

Result schema

What this Tool does

Inputs and conditions

Returned information

Price and account

Limits and freshness

Source and verification

Collect one webpage

Collect several webpages together

Submit a list of pages

Questions about this tool.

You receive

Start with your task

Inputs & outputs

Input schema

Result schema

What this Tool does

Inputs and conditions

Returned information

Price and account

Limits and freshness

Source and verification

Collect one webpage

Collect several webpages together

Submit a list of pages

Questions about this tool.

What input does this Tool need?

What does the result prove?

How is this Tool charged?

What if the result is empty or a field is missing?

How do I use this Tool with my Agent?