ShotAPI logo

ShotAPI

Captures webpages and renders agent-written HTML/CSS through MCP tools, with remote HTTP and local stdio options.

Install ShotAPI

Pick your client, then add it in one click or paste the config.

No confirmed install command yet

We only publish a config when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for ShotAPI, and we’d rather show nothing than a guess you’d paste into your client.

Open setup steps on GitHub

Overview

The ShotAPI MCP server gives AI agents tools to capture webpages and turn HTML/CSS into images. It supports a remote streamable-HTTP endpoint with no local installation, or a local stdio bridge backed by Python and Playwright. Use it to inspect deployed pages, validate generated interfaces, or create visual outputs during development. Its tools cover quick screenshots, configurable captures, and HTML rendering.

Use cases

  • Capture a deployed webpage for visual verification
  • Render agent-generated HTML and CSS
  • Inspect a CSS selector or full-page layout
  • Automate before-and-after screenshots in CI

Key features

  • Quick URL screenshots
  • Viewport and full-page capture
  • CSS selector screenshots
  • HTML/CSS rendering
  • Remote streamable HTTP
  • Local stdio mode

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

5/5 checks healthy over the last 44d

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
Last commit4mo agoMost recent push to the default branch.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How ShotAPI works

What ShotAPI MCP server does

The ShotAPI MCP server exposes browser-based screenshot and rendering functions to MCP-compatible AI clients. An agent can capture a webpage from a URL, request a more controlled screenshot, or submit HTML and CSS for image rendering. This supports visual checks after an agent writes interface code, deployment reviews, and basic screenshot-based regression workflows.

The service can capture an existing page or render content supplied directly by the agent. Screenshots can use a specified viewport, capture the full page, target a CSS selector, and choose an output format. The service also includes ad blocking, which can reduce unrelated page content in captures.

How it works

In remote mode, an MCP client connects to the streamable-HTTP endpoint at https://aiphotoshop.mynatapp.cc/mcp. The client then exposes ShotAPI's functions in the agent conversation. Claude Code can be configured with its MCP command, while Claude Desktop and Cursor can use an MCP server entry with the endpoint URL.

The three available tools serve different purposes:

  • screenshot_one_liner captures one URL with a minimal call.
  • screenshot provides controls for viewport size, full-page capture, CSS selectors, and image format.
  • render converts agent-supplied HTML and CSS into an image.

The render workflow is useful when an agent needs to write markup, inspect the resulting visual output, make a correction, and render it again. The HTTP service also exposes screenshot requests through a versioned endpoint, which can be called directly with curl for non-MCP workflows.

Setup and configuration

Remote use requires no Python, Playwright installation, API key, or signup on the documented free tier. Add the streamable-HTTP URL to the MCP client's configuration, or pass it to Claude Code with the MCP command shown in the project documentation.

For local stdio mode, install the Python dependencies from requirements.txt, install Chromium through Playwright, and run mcp_stdio.py. Set SHOTAPI_BASE_URL to the ShotAPI service URL.

The documented free tier allows 50 screenshots and 50 renders per month, uses IP-based limits, and does not require an API key. Paid plans increase the monthly limits and provide a key through the pricing page.

Tools and capabilities

The ShotAPI MCP server is suited to agents that need visual feedback rather than only textual or DOM-level inspection. It can:

  • Capture a single webpage from a URL.
  • Capture a full page or a selected CSS element.
  • Adjust viewport settings and output format.
  • Render HTML/CSS written by an agent.
  • Support remote streamable HTTP or local stdio operation.
  • Provide direct HTTP screenshot access for scripts and CI workflows.

Limitations and notes

Usage is limited by the selected plan. The free service uses IP-based quotas of 50 screenshots and 50 renders per month, while the listed paid plans provide 5,000 or 20,000 monthly requests. Local mode still requires the Python dependencies and a Chromium installation.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about ShotAPI

ShotAPI is an MCP server that connects AI agents to a web screenshot and HTML rendering service through streamable HTTP or a local stdio bridge. Its main tools are screenshot_one_liner for quick captures, screenshot for viewport and selector controls, and render for converting HTML/CSS into images.

You do not need to install it for remote mode: add its streamable-HTTP URL to your MCP client. For local mode, install the Python requirements, install Chromium with Playwright, set SHOTAPI_BASE_URL, and run mcp_stdio.py.

Yes, ShotAPI works with Cursor through a streamable-HTTP MCP configuration. Add a server entry using the URL https://aiphotoshop.mynatapp.cc/mcp, then Cursor can access the documented screenshot and render tools.

The render tool converts HTML and CSS supplied by the agent into an image. It lets an agent inspect generated interface code visually, identify layout issues, revise the code, and render the result again.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewShotAPI AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/shotapi?style=directory)](https://allmcps.com/mcp/shotapi)
HTML Embed
<a href="https://allmcps.com/mcp/shotapi"><img src="https://allmcps.com/api/badge/shotapi?style=directory" alt="ShotAPI on AllMCPs" /></a>