What is the ScreenshotOne MCP server?

A hosted Model Context Protocol server at https://mcp.screenshotone.com that connects your ScreenshotOne account to any MCP-aware AI client. Your agent can render website screenshots, split long pages into full-page slices, and extract clean page content as Markdown.

Which clients are supported?

Claude, Claude Code, ChatGPT, Codex, and Cursor are covered in the MCP guide. GitHub Copilot, Gemini, Windsurf, OpenCode, OpenClaw, and any other client work too, as long as they support remote HTTP MCP servers with OAuth. The endpoint is the same everywhere.

Do I need to run anything locally or paste an API key?

No. The server is hosted at https://mcp.screenshotone.com, and you connect with OAuth in the browser. If you prefer a local setup, an open-source command-line server is also available on GitHub.

MCP vs the API: which should I use?

Use MCP when you work through an AI client like Claude Code, Cursor, or ChatGPT and want to ask for screenshots in natural language. Use the API when you build your own server integration or automation and need full control over requests, options, and responses.

Do MCP tool calls use my credits?

Yes. Each tool call runs as a regular ScreenshotOne API request on your account and costs 1 credit, whether it is a screenshot or Markdown. You can start free with 100 credits a month and no credit card.

Is my data or token sent anywhere else?

No. Your client talks to mcp.screenshotone.com, which renders pages through the ScreenshotOne API. You connect with OAuth, so no ScreenshotOne API key is pasted into the client, and you can revoke a connected client at any time from the MCP connections page in the dashboard.

Give your AI agents eyes for the web

Use the ScreenshotOne MCP to give your agents screenshots of any web page, without ads or cookie banners, plus the page text as clean Markdown.

https://mcp.screenshotone.com

Works with every MCP client:

Start rendering →Read the guide

Stripe brand colorsPull a brand palette from a screenshot

What are Stripe's brand colors? Check stripe.com and give me CSS variables for a comparison slide.

render-website-screenshot

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://stripe.com"}

screenshot.jpg

Stripe's home page pairs a tight core palette with a bright ribbon gradient:

Navy #061B31 for headlines and navigation
Blurple #533AFD for buttons and accents
Slate #64748D for supporting headline text
Ribbon #B4BDFE #FE9A15 #FE5B66 #FE85E5 #8D60F0 in the hero

:root {  --stripe-navy: #061B31;  --stripe-blurple: #533AFD;  --stripe-slate: #64748D;  --stripe-ribbon: linear-gradient(    120deg,    #B4BDFE, #FE9A15, #FE5B66, #FE85E5, #8D60F0  );}

The ribbon stops are sampled from the screenshot, so treat them as close approximations.

leads.csv

Go through these leads, screenshot each homepage, and add a note on what to improve. Then tell me which pitches are strongest.

Found 3 leads in leads.csv. Capturing each homepage now.

render-website-screenshot

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://boltai.com"}

render-website-screenshot

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://userjot.com"}

render-website-screenshot

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://framekit.ai"}

Done. I added a notes column to leads.csv:

company,website,notesBoltAI,boltai.com,"Clear headline and CTAs; customer logos start below the fold"UserJot,userjot.com,"Right half of the hero is empty; product preview starts below the fold"Framekit,framekit.ai,"A news popup covers the headline and subheadline on first load"

Strongest pitches:

1.Framekit: show the Cadence announcement as a small banner instead of a popup over the hero.
2.UserJot: move the product preview next to the headline so the hero shows the tool at a glance.
3.BoltAI: the hero already works, so pitch pulling the customer logos above the fold instead of a redesign.

Read stripe.com/pricing. How much would Stripe keep from a $50 card payment?

extract-website-markdown

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://stripe.com/pricing"}

# Pricing built for businesses of all sizes ## Standard Access a complete payments platform with simple, pay-as-you-go pricing. No setup fees, monthly fees, or hidden fees. **2.9% + 30¢** per successful transaction for domestic cards - + 0.5% for manually entered cards- + 1.5% for international cards- + 1% if currency conversion is required

With standard pricing, Stripe keeps $1.75 from a $50 domestic card payment, so you receive $48.25:

1.2.9% of $50 is $1.45
2.The fixed fee is $0.30

For an international card, add 1.5% and the fee becomes $2.50. If currency conversion is also needed, another 1% brings it to $3.00.

What did Linear ship this week? Check their changelog and tell me what matters for a small team.

extract-website-markdown

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://linear.app/changelog"}

# Changelog ## New controls for Linear coding agent September 24, 2026 ### Adaptive routingSave time and tokens by automatically routing simpler tasks to a faster model. ### Environment secretsCoding sessions can now access environment secrets during setup. ## Team organization at scale - Team project labels and statuses- Project lead teams- Team loops triggers- Project and initiative IDs

Linear's September 24 update has two parts:

Coding agent controls: adaptive routing sends simpler tasks to a faster model, sessions can read environment secrets, and open-weight models are now supported.
Team organization: teams get their own project labels and statuses, projects can have a lead team, and loops can trigger on team changes.

For a small team, adaptive routing is the one to try: it saves tokens on routine issues without any setup. Team project labels and statuses are only on Business and Enterprise plans.

We just shipped new pricing. Check screenshotone.com/pricing and confirm the plans show $17, $79, and $259, and that nothing looks broken.

render-website-screenshot

Calling ScreenshotOne…ScreenshotOne · Completed

{ "url": "https://screenshotone.com/pricing/", "full_page": true, "full_page_slices": true}

Slice 1 of the ScreenshotOne pricing page — slice 1

Slice 2 of the ScreenshotOne pricing page — slice 2

Slice 3 of the ScreenshotOne pricing page — slice 3

The release looks good. I reviewed the full page in three slices:

Basic $17, Growth $79, and Scale $259 per month
Growth is marked Recommended
The billing toggle, testimonial, and FAQ render without overlaps
No broken images or missing sections down to the footer

I can rerun this check after each deploy and attach the slices to the release notes.

"Great support."

Guillaume Barillot, CTO at Deepidoo

"Great company, great founder!"

Mike Roberts, Founder at SpyFu

"ScreenshotOne is the way to go."

Lukas Hermann, Co-Founder of Stagetimer

Workflows

Give agents context they can use

Screenshots show how a page looks, and Markdown shows what it says. Together they let your agent check, compare, and report on any page.

Verify the live page

Let an agent capture the rendered result after a release and include visual proof with its QA summary.

Read the use case

Research with visual context

Combine a screenshot with clean Markdown when an agent needs to understand both how a page looks and what it says.

Read the use case

Monitor visible changes

Use ScreenshotOne inside a scheduled agent or automation workflow to capture the same page over time.

Read the use case

Attach evidence to results

Return temporary image URLs and full-page slices an agent can inspect or preserve with a report.

Read the use case

Track competitor pricing

Have an agent read competitor pricing pages as Markdown and keep a screenshot of each plan table it compares.

Read the use case

Review landing pages

Give an agent the rendered page and its copy so it can critique the layout, messaging, and calls to action.

Read the use case

Thomas Sanlis

Founder,Uneed

ScreenshotOne is so simple to use I didn't even realized my agents used it to take screenshots. I followed the journey of ScreenshotOne since the beginning, and it's among the few products I can put 100% of my trust in.

Read how Uneed uses ScreenshotOne with AI agents →

Frequently Asked Questions

Quick answers to common questions about the ScreenshotOne MCP and giving your agents web page screenshots and text.

What is the ScreenshotOne MCP server?: A hosted Model Context Protocol server at https://mcp.screenshotone.com that connects your ScreenshotOne account to any MCP-aware AI client. Your agent can render website screenshots, split long pages into full-page slices, and extract clean page content as Markdown.
Which clients are supported?: Claude, Claude Code, ChatGPT, Codex, and Cursor are covered in the MCP guide. GitHub Copilot, Gemini, Windsurf, OpenCode, OpenClaw, and any other client work too, as long as they support remote HTTP MCP servers with OAuth. The endpoint is the same everywhere.
Do I need to run anything locally or paste an API key?: No. The server is hosted at https://mcp.screenshotone.com, and you connect with OAuth in the browser. If you prefer a local setup, an open-source command-line server is also available on GitHub.
MCP vs the API: which should I use?: Use MCP when you work through an AI client like Claude Code, Cursor, or ChatGPT and want to ask for screenshots in natural language. Use the API when you build your own server integration or automation and need full control over requests, options, and responses.
Do MCP tool calls use my credits?: Yes. Each tool call runs as a regular ScreenshotOne API request on your account and costs 1 credit, whether it is a screenshot or Markdown. You can start free with 100 credits a month and no credit card.
Is my data or token sent anywhere else?: No. Your client talks to mcp.screenshotone.com, which renders pages through the ScreenshotOne API. You connect with OAuth, so no ScreenshotOne API key is pasted into the client, and you can revoke a connected client at any time on the MCP connections page.

Read

Guides and stories from agent builders

How teams connect ScreenshotOne to their agents, and what they build with screenshots and Markdown.

Screenshot Rendering AI Agents

agent-browser screenshots: full-page capture, elements, and saving files

Take screenshots with Vercel Labs' agent-browser. Capture a viewport, full page, or element; save PNG or JPEG files; and control image resolution.

Written by: Dmytro Krasun
Published on: Sep 27, 2026; 4 min read

Playwright Guides Screenshot Rendering AI Agents

Playwright MCP screenshots: full-page capture, elements, and saving files

Set up Playwright MCP, capture viewport, full-page, and element screenshots, choose image resolution, and find the saved files.

Written by: Dmytro Krasun
Published on: Sep 27, 2026; 6 min read

Screenshot Rendering AI Agents

Chrome DevTools MCP screenshots: capture, save, and resize images

Take viewport, full-page, and element screenshots with Chrome DevTools MCP. Save PNG, JPEG, or WebP files and control image dimensions.

Written by: Dmytro Krasun
Published on: Sep 27, 2026; 6 min read

Automate website screenshots

Exhaustive documentation, ready SDKs, no-code tools, and other automation to help you render website screenshots and outsource all the boring work related to that to us.

Start rendering →Book a call

Give your AI agents eyes for the web

Give agents context they can use

Verify the live page

Research with visual context

Monitor visible changes

Attach evidence to results

Track competitor pricing

Review landing pages

Frequently Asked Questions

Guides and stories from agent builders

agent-browser screenshots: full-page capture, elements, and saving files

Playwright MCP screenshots: full-page capture, elements, and saving files

Chrome DevTools MCP screenshots: capture, save, and resize images

Automate website screenshots

Integrations

Use Cases

Screenshot Tools

Customers