CaptureOneAI Web Perception

com.captureoneaiPublished by captureoneai.comOfficial publisherv1.0.0Updated Oct 24, 2026

Give agents eyes on any web page: structured context, and changes explained in plain language.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser Automation

Overview

AI-generated overview

Lets an assistant read structured web page content and monitor pages for meaningful changes explained in plain language.

What you can do
Provides tools to capture a page's structured representation, including visible text with coordinates, interactive elements, forms and tables, and to list only clickable elements with roles, labels, selectors and pixel coordinates. It also creates scheduled semantic monitors for a URL, lists and manually triggers monitors, and returns recent check history with detected changes, their relevance and an AI explanation.
When to use it
Useful when an assistant needs to understand or act on a web page without parsing raw HTML, or when you want to watch competitor pricing pages, changelogs or status pages and be told what changed and whether it matters.
Requirements
A remote MCP endpoint at captureoneai.com over streamable HTTP; no packages, environment variables or headers are declared. Network access to the service is required.
Before you install
Monitors are created and stored on the remote service and can be triggered on demand, so page URLs you submit are sent to a third party. No authentication is declared, so check how monitors are tied to your account before relying on it.

Installation

In SourceWeft

  1. Open CaptureOneAI Web Perception in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.captureoneai%2Fweb-perception/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "captureoneai-web-perception": {
      "type": "http",
      "url": "https://captureoneai.com/mcp"
    }
  }
}

Tools

6

capture_context

Capture page context

Returns the structured representation of a web page: visible text with coordinates, interactive elements, forms and tables. Use this to let an agent read and understand a page without parsing raw HTML.

ParametersurlrequiredwidthheightdismissCookies

find_elements

Find interactive elements

Returns only the interactive elements of a page (buttons, links, inputs) with role, label, CSS selector and pixel coordinates. Use this before acting on a page (computer-use / Set-of-Marks style grounding) instead of capture_context when you only need to know what can be clicked and where.

ParametersurlrequiredwidthheightdismissCookies

create_semantic_monitor

Create a semantic monitor

Watches a URL on a schedule and reports what changed and whether it matters, explained by AI — not just a pixel-diff percentage. Use this for competitor pricing pages, changelogs, status pages, or any page whose changes should trigger a workflow.

ParametersurlrequiredlabelintentschedulecallbackUrl

list_monitors

List monitors

Lists your active monitors and their IDs, URLs and schedules.

Takes no parameters.

check_monitor

Check a monitor now

Triggers an immediate check for a monitor instead of waiting for its next scheduled run, and returns any detected changes.

ParametersmonitorIdrequired

get_monitor_changes

Get monitor change history

Returns the recent check history for a monitor, including detected changes with their relevance and explanation.

ParameterslimitmonitorIdrequired

Version history

1
  1. v1.0.0LatestSep 21, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.