URLpipe
Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.
Should I use this
Quality & Safety
A
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
~10,820Tokens (tool definitions)
~7.8 KBTypical response size
Significant attention impact (8.45% of 128k context)
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp": {
"url": "https://urlpipe.dev/mcp"
}
}
}Remote endpoints
https://urlpipe.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (14)
🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢list_projects
The projects this token can reach, each with how many requests it has made in the last 30 days and where its results are delivered. Start here: every other tool takes a project_id from this list. A project is the unit a request is billed and recorded against — credits themselves belong to the organization, so which project you pick does not change what a call costs.
Input Schema
{
"type": "object",
"properties": {},
"required": [],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"organization": {
"type": "string"
},
"projects": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"name"
],
"properties": {
"id": {
"type": "integer"
},
"name": {
"type": "string"
},
"default_webhook_url": {
"type": "string"
},
"requests_last_30_days": {
"type": "integer"
}
}
}
}
},
"required": [
"organization",
"projects"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_usage
What the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen times in price, so the difference between fetch_markdown and summarize_page over a hundred pages is 100 credits against 1,700. It is also how to read a refusal — a call that comes back with quota_exceeded is telling you this number ran out.
Input Schema
{
"type": "object",
"properties": {},
"required": [],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"plan": {
"type": "string"
},
"plan_name": {
"type": "string"
},
"credits": {
"type": "object",
"properties": {
"limit": {
"type": [
"integer",
"string"
],
"description": "A number, or \"unlimited\"."
},
"used": {
"type": "integer"
},
"remaining": {
"type": [
"integer",
"string"
],
"description": "A number, or \"unlimited\"."
},
"resets_at": {
"type": "string"
}
}
},
"concurrency_limit": {
"type": "integer"
},
"cost_per_operation": {
"type": "object",
"additionalProperties": {
"type": "integer"
}
},
"residential_surcharge_per_page_visit": {
"type": "integer"
}
},
"required": [
"plan",
"credits",
"cost_per_operation"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟡fetch_markdown(project_id, url, sync, max_age, residential, ...)
Exposes POST /markdown. Renders the page in headless Chrome and converts its main content to clean Markdown — headings, lists, links and code kept, navigation, sidebars and cookie banners dropped. Start here when you want to READ a page. It is the cheapest operation we sell (1 credit) and by far the most compact thing to put in front of a model: fetch_html returns the whole DOM, which is usually many times larger and says nothing extra about what the page means.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"markdown"
],
"properties": {
"markdown": {
"type": "string",
"description": "The page's main content as Markdown."
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡fetch_html(project_id, url, sync, max_age, residential, ...)
Exposes POST /html. Returns the page's HTML after JavaScript has run and redirects have been followed — the DOM a real browser sees, not the empty shell curl returns. 1 credit. Use it when you need the markup itself: a specific attribute, a script tag, a structured-data block. If you want to read the page's content, fetch_markdown costs the same and returns a fraction of the text.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"description": "The rendered HTML."
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡capture_screenshot(project_id, url, sync, max_age, residential, ...)
Exposes POST /screenshot. Captures the whole rendered page as a PNG — JavaScript executed, web fonts and images included, exactly as a browser would draw it. 1 credit, whichever options you use. Use it to see a page rather than read it: layout, visual regressions, link previews, or checking what an anti-bot page actually showed us. screenshot_options size it (viewport, scale, one element, the fold only), encode it (png, jpeg or webp) and restyle it (dark mode, hidden elements, your own CSS); page_options wait for the page and take ads and cookie banners out of it.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"screenshot_options": {
"type": "object",
"description": "How to take the screenshot. Every key is optional; leave it out for a full-page PNG.",
"properties": {
"full_page": {
"type": "boolean",
"description": "Capture the whole page top to bottom (default true). false captures the viewport only."
},
"full_page_max_height": {
"type": "integer",
"description": "The tallest a full-page or element capture may be, in CSS pixels: 100 to 16384, the default."
},
"viewport_width": {
"type": "integer",
"description": "Browser viewport width in CSS pixels, 320 to 1920. Default 1350."
},
"viewport_height": {
"type": "integer",
"description": "Browser viewport height in CSS pixels, 240 to 1080. Default 797."
},
"device_scale_factor": {
"type": "integer",
"description": "Pixel density, 1 to 3: 2 gives a retina image twice the size. Default 1."
},
"format": {
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
],
"description": "Image format. Default png; webp is usually the smallest."
},
"quality": {
"type": "integer",
"description": "jpeg and webp only, 1 to 100. Default 80."
},
"omit_background": {
"type": "boolean",
"description": "Transparent background where the page sets none. png and webp only."
},
"selector": {
"type": "string",
"description": "CSS selector of one element to capture instead of the page."
},
"dark_mode": {
"type": "boolean",
"description": "Render with prefers-color-scheme: dark."
},
"hide_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to hide before capturing, up to 50. They stay in the page's html; page_options.remove_selectors takes them out of it."
},
"styles": {
"type": "string",
"description": "CSS to inject into the page before capturing."
}
}
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"mime_type"
],
"properties": {
"mime_type": {
"type": "string",
"description": "The image's type. The image itself is the image content block."
},
"result_url": {
"type": [
"string",
"null"
],
"description": "A link to the image that needs no key."
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡capture_console_errors(project_id, url, sync, max_age, residential, ...)
Exposes POST /console. Loads the page in headless Chrome and returns what it reported through console.error and console.warn during load, plus uncaught exceptions and unhandled promise rejections (not console.log). 1 credit. What you would open DevTools for: broken third-party scripts and client-side errors you cannot reproduce locally.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"entries"
],
"properties": {
"entries": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"error",
"warning",
"exception"
]
},
"text": {
"type": "string"
}
}
}
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡run_lighthouse_audit(project_id, url, sync, max_age, residential, ...)
Exposes POST /lighthouse. Runs a real Google Lighthouse audit against the live page: performance, accessibility, best-practices and SEO scores plus Core Web Vitals. 2 credits — dearer than a page fetch because the audit runs in its own limited lane, so it also takes longer than anything else here. It fetches the page itself rather than sharing a visit, so asking for it inside scrape_url costs two page visits, not one.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"device": {
"type": "string",
"enum": [
"mobile",
"desktop"
],
"description": "Which profile to audit under. Default mobile."
},
"include_audits": {
"type": "boolean",
"description": "Include the full per-audit detail, not just scores and metrics. Much larger; default false."
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"fetchTime": {
"type": "string"
},
"device": {
"type": "string"
},
"categories": {
"type": "object"
},
"metrics": {
"type": "object"
},
"audits": {
"type": "object"
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡extract_metadata(project_id, url, sync, max_age, residential, ...)
Exposes POST /meta. Reconciles Open Graph, Twitter card and standard page metadata into one clean object: title, description, language, main image, favicon, author, publication date and feed. Values injected by JavaScript are included, because the page is rendered first. 5 credits. This is the page's metadata, not a dump of its meta tags. If you only need the title, it is also in the Markdown — and that costs 1 credit.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"language": {
"type": [
"string",
"null"
]
},
"main_image_url": {
"type": [
"string",
"null"
]
},
"favicon_url": {
"type": [
"string",
"null"
]
},
"author_name": {
"type": [
"string",
"null"
]
},
"feed_url": {
"type": [
"string",
"null"
]
},
"publication_date": {
"type": [
"string",
"null"
]
},
"additional_author_information": {
"type": [
"object",
"null"
]
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡extract_keywords(project_id, url, sync, max_age, residential, ...)
Exposes POST /keywords. Returns the 5–15 terms and phrases that best represent the page, ordered by relevance — ranked by a language model, not by raw frequency. 15 credits. As with summarize_page: if you are going to reason over the result yourself, fetch_markdown costs 1 credit and gives you everything.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"keywords"
],
"properties": {
"keywords": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡summarize_page(project_id, url, sync, max_age, residential, ...)
Exposes POST /summarize. Returns a concise Markdown summary of the page's main content, with the navigation, ads and boilerplate left out. The most expensive operation we sell, at 17 credits, because it runs a language model over the page. If YOU are the model that will read it, fetch_markdown gives you the whole page for 1 credit and you can summarize it yourself — this tool is for when the summary is the artefact being produced, not a step on the way to one.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string",
"description": "A Markdown summary of the page."
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟡scrape_url(project_id, url, sync, max_age, residential, ...)
Exposes POST /scrape. Runs any subset of the other operations in one request, served from a single page visit where possible. Each operation is billed and stored exactly as the individual call would be, so this is not a discount — with one exception, and it is the reason to use it: a residential exit is charged per page VISIT, so several results off one visit pay the surcharge once. Answers with one object keyed by operation, each entry carrying its own success and result, so a partial failure still returns everything that worked. lighthouse does not share the visit — it runs its own audit on its own engine — so including it means two page fetches, and two surcharges when residential is on. So does a screenshot whose screenshot_options set viewport_width, viewport_height, device_scale_factor, dark_mode or block_ads: those change how the page loads, so the screenshot gets a visit of its own.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "Which project this request belongs to. From list_projects."
},
"url": {
"type": "string",
"description": "The page to fetch. Must be a public http(s) URL."
},
"sync": {
"type": "boolean",
"description": "Wait for the result and return it (default false). When false the call returns a token immediately and you collect the result with get_result."
},
"max_age": {
"type": "string",
"description": "How fresh a stored result must be to be reused, e.g. \"2 hours\" or \"3 days\". Default 7 days, maximum 30. A reused result is free. Pass \"0\" to force a fresh fetch."
},
"residential": {
"type": "boolean",
"description": "Fetch the page from a residential (home ISP) exit instead of a datacentre one. Costs a surcharge per page visit — see get_usage. Use it for sites that block datacentre traffic."
},
"report_to": {
"type": "string",
"description": "Async only: a webhook URL to deliver the result to. Defaults to the project's configured endpoint, if it has one."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Your own keys to find this request by later, e.g. {\"client\": \"acme\"}: they come back with the result, in the webhook and in list_requests, which can filter by them. Up to 16 keys of up to 40 letters, digits, _ - or .; string values up to 256 characters."
},
"idempotency_key": {
"type": "string",
"description": "Makes the call safe to retry: sending it again with the same key within 24 hours returns the first call's token and result instead of starting (and charging for) new work, even with max_age \"0\". Up to 255 printable ASCII characters; a UUID is ideal."
},
"operations": {
"type": "array",
"items": {
"type": "string",
"enum": [
"html",
"screenshot",
"markdown",
"meta",
"summarize",
"keywords",
"lighthouse",
"console"
]
},
"description": "Which operations to run off this page."
},
"device": {
"type": "string",
"enum": [
"mobile",
"desktop"
],
"description": "Lighthouse only, when it is among the operations. Default mobile."
},
"include_audits": {
"type": "boolean",
"description": "Lighthouse only: include the full per-audit detail. Default false."
},
"screenshot_options": {
"type": "object",
"description": "Screenshot only, when it is among the operations: how to take it, exactly as capture_screenshot takes it.",
"properties": {
"full_page": {
"type": "boolean",
"description": "Capture the whole page top to bottom (default true). false captures the viewport only."
},
"full_page_max_height": {
"type": "integer",
"description": "The tallest a full-page or element capture may be, in CSS pixels: 100 to 16384, the default."
},
"viewport_width": {
"type": "integer",
"description": "Browser viewport width in CSS pixels, 320 to 1920. Default 1350."
},
"viewport_height": {
"type": "integer",
"description": "Browser viewport height in CSS pixels, 240 to 1080. Default 797."
},
"device_scale_factor": {
"type": "integer",
"description": "Pixel density, 1 to 3: 2 gives a retina image twice the size. Default 1."
},
"format": {
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
],
"description": "Image format. Default png; webp is usually the smallest."
},
"quality": {
"type": "integer",
"description": "jpeg and webp only, 1 to 100. Default 80."
},
"omit_background": {
"type": "boolean",
"description": "Transparent background where the page sets none. png and webp only."
},
"selector": {
"type": "string",
"description": "CSS selector of one element to capture instead of the page."
},
"dark_mode": {
"type": "boolean",
"description": "Render with prefers-color-scheme: dark."
},
"hide_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to hide before capturing, up to 50. They stay in the page's html; page_options.remove_selectors takes them out of it."
},
"styles": {
"type": "string",
"description": "CSS to inject into the page before capturing."
}
}
},
"page_options": {
"type": "object",
"description": "What to do to the page before anything is read off it. Applies to the result itself: removed ads and banners are gone from html, markdown and summaries too.",
"properties": {
"wait_for_selector": {
"type": "string",
"description": "Wait (up to 10s) for an element matching this CSS selector before reading the page."
},
"delay": {
"type": "integer",
"description": "Milliseconds to wait after the page has settled, 0 to 10000."
},
"block_ads": {
"type": "boolean",
"description": "Block the major ad networks and remove their slots from the page."
},
"block_cookie_banners": {
"type": "boolean",
"description": "Remove cookie-consent banners from the page."
},
"remove_selectors": {
"type": "array",
"items": {
"type": "string"
},
"description": "CSS selectors of elements to remove from the page, up to 50."
}
}
}
},
"required": [
"project_id",
"url",
"operations"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"operations": {
"type": "object",
"description": "One key per operation requested, in the order asked for.",
"additionalProperties": {
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"result": {},
"error": {
"type": "string"
},
"cached": {
"type": "boolean"
}
}
}
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "accepted"
},
"labels": {
"type": "object"
}
}
}
]
}🟢get_result(project_id, token)
Exposes GET /result/:token. Returns the result of a past request, in the same form the call that made it would have returned — Markdown as Markdown, a structured operation as its object, a screenshot as an image, a scrape as its combined object. This is how an async call is collected: any tool called without sync: true answers with a token, and this turns that token into the result. It also re-reads a result somebody already paid for, which is free — results are kept for 30 days. A request that has not finished yet answers {"status": "processing"}; call again in a moment.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "From list_projects."
},
"token": {
"type": "string",
"description": "The token the original call returned."
}
},
"required": [
"project_id",
"token"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"anyOf": [
{
"type": "object",
"required": [
"markdown"
],
"properties": {
"markdown": {
"type": "string",
"description": "The page's main content as Markdown."
}
}
},
{
"type": "object",
"required": [
"html"
],
"properties": {
"html": {
"type": "string",
"description": "The rendered HTML."
}
}
},
{
"type": "object",
"required": [
"summary"
],
"properties": {
"summary": {
"type": "string",
"description": "A Markdown summary of the page."
}
}
},
{
"type": "object",
"required": [
"keywords"
],
"properties": {
"keywords": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
{
"type": "object",
"required": [
"entries"
],
"properties": {
"entries": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"error",
"warning",
"exception"
]
},
"text": {
"type": "string"
}
}
}
}
}
},
{
"type": "object",
"required": [
"mime_type"
],
"properties": {
"mime_type": {
"type": "string",
"description": "The image's type. The image itself is the image content block."
},
"result_url": {
"type": [
"string",
"null"
],
"description": "A link to the image that needs no key."
}
}
},
{
"type": "object",
"properties": {
"title": {
"type": [
"string",
"null"
]
},
"description": {
"type": [
"string",
"null"
]
},
"language": {
"type": [
"string",
"null"
]
},
"main_image_url": {
"type": [
"string",
"null"
]
},
"favicon_url": {
"type": [
"string",
"null"
]
},
"author_name": {
"type": [
"string",
"null"
]
},
"feed_url": {
"type": [
"string",
"null"
]
},
"publication_date": {
"type": [
"string",
"null"
]
},
"additional_author_information": {
"type": [
"object",
"null"
]
}
}
},
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"fetchTime": {
"type": "string"
},
"device": {
"type": "string"
},
"categories": {
"type": "object"
},
"metrics": {
"type": "object"
},
"audits": {
"type": "object"
}
}
},
{
"type": "object",
"properties": {
"url": {
"type": "string"
},
"operations": {
"type": "object",
"description": "One key per operation requested, in the order asked for.",
"additionalProperties": {
"type": "object",
"properties": {
"success": {
"type": "boolean"
},
"result": {},
"error": {
"type": "string"
},
"cached": {
"type": "boolean"
}
}
}
}
}
},
{
"type": "object",
"required": [
"token",
"status"
],
"properties": {
"token": {
"type": "string"
},
"status": {
"type": "string",
"const": "processing"
},
"labels": {
"type": "object"
}
}
}
]
}🟢list_requests(project_id, url, operation, labels, limit, ...)
A project's recent requests, newest first, with each one's token. Look here before fetching a page: if somebody already pulled it, passing that token to get_result returns the same result for nothing. A /scrape appears as one entry — its per-operation children are internal, and the scrape's own token returns all of them. Pass labels to see only the requests made with them — every key given must match its value exactly.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "From list_projects."
},
"url": {
"type": "string",
"description": "Only requests for this exact URL."
},
"operation": {
"type": "string",
"enum": [
"html",
"screenshot",
"markdown",
"meta",
"summarize",
"keywords",
"lighthouse",
"console",
"scrape"
],
"description": "Only requests running this operation."
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only requests made with all of these labels, each value matched exactly."
},
"limit": {
"type": "integer",
"description": "How many to return. Default 25, maximum 100."
},
"offset": {
"type": "integer",
"description": "Skip this many, for paging."
}
},
"required": [
"project_id"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer"
},
"total": {
"type": "integer"
},
"offset": {
"type": "integer"
},
"requests": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"url",
"status"
],
"properties": {
"token": {
"type": "string"
},
"url": {
"type": "string"
},
"operation": {
"type": [
"string",
"null"
]
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"status": {
"type": "string"
},
"success": {
"type": [
"boolean",
"null"
]
},
"served_from_cache": {
"type": [
"boolean",
"null"
]
},
"credits": {
"type": "integer"
},
"created_at": {
"type": "string"
},
"finished_at": {
"type": "string"
},
"duration_ms": {
"type": "integer"
}
}
}
}
},
"required": [
"project_id",
"total",
"offset",
"requests"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢get_request(project_id, token)
Everything about one past request except its result: what was asked for, how long each stage took, whether it came from the store, and how the webhook delivery went. This is the metadata; get_result returns the page itself. Reach for this one when a call did not do what you expected — it says whether the result was reused, why an analysis failed, and whether the delivery to the project's endpoint succeeded.
Input Schema
{
"type": "object",
"properties": {
"project_id": {
"type": "integer",
"description": "From list_projects."
},
"token": {
"type": "string",
"description": "The token the original call returned."
}
},
"required": [
"project_id",
"token"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Output Schema
{
"type": "object",
"properties": {
"token": {
"type": "string"
},
"url": {
"type": "string"
},
"operation": {
"type": [
"string",
"null"
]
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"status": {
"type": "string"
},
"success": {
"type": [
"boolean",
"null"
]
},
"served_from_cache": {
"type": [
"boolean",
"null"
]
},
"credits": {
"type": "integer"
},
"created_at": {
"type": "string"
},
"finished_at": {
"type": "string"
},
"duration_ms": {
"type": "integer"
},
"request_options": {
"type": [
"object",
"null"
]
},
"max_age": {
"type": [
"integer",
"null"
]
},
"async": {
"type": [
"boolean",
"null"
]
},
"outcome": {
"type": [
"object",
"null"
]
},
"report_to": {
"type": [
"string",
"null"
]
},
"webhook_status": {
"type": [
"string",
"null"
]
},
"webhook_delivered_at": {
"type": [
"string",
"null"
]
},
"webhook_error": {
"type": [
"string",
"null"
]
},
"operations": {
"type": "array",
"items": {
"type": "object",
"required": [
"token",
"url",
"status"
],
"properties": {
"token": {
"type": "string"
},
"url": {
"type": "string"
},
"operation": {
"type": [
"string",
"null"
]
},
"labels": {
"type": "object",
"additionalProperties": {
"type": "string"
}
},
"status": {
"type": "string"
},
"success": {
"type": [
"boolean",
"null"
]
},
"served_from_cache": {
"type": [
"boolean",
"null"
]
},
"credits": {
"type": "integer"
},
"created_at": {
"type": "string"
},
"finished_at": {
"type": "string"
},
"duration_ms": {
"type": "integer"
}
}
}
},
"meta": {
"type": "object",
"description": "What the HTTP response headers would say: cache, cost, quota, result_url."
}
},
"required": [
"token",
"url",
"status"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Community
Evidence
Recent observations
verifiedversion not recorded14 tools