CaptureOneAI Web Perception
Server Details
Give agents eyes on any web page: structured context, and changes explained in plain language.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Most tools are clearly distinct: capture_context and find_elements have some overlap as both return page structure, but descriptions clarify that find_elements is specifically for interactive element grounding. The monitor tools (create, list, check, get changes) are unambiguous.
All tools consistently follow a verb_noun pattern using snake_case: capture_context, create_semantic_monitor, check_monitor, find_elements, get_monitor_changes, list_monitors. The naming is predictable and easy to infer.
Six tools is well-suited for a web perception and monitoring server. Each tool covers a distinct capability without redundancy or bloat, and the count feels appropriately scoped for the domain.
The core workflows—understanding a page, locating interactive elements, creating/list/checking monitors, and retrieving change history—are well covered. A minor gap is the lack of delete/update operations for monitors, but the existing surface handles the primary perception and monitoring use cases.
Available Tools
6 toolscapture_contextCapture page contextBInspect
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.
Inputs: url (required), width, height, dismissCookies.
check_monitorCheck a monitor nowAInspect
Triggers an immediate check for a monitor instead of waiting for its next scheduled run, and returns any detected changes.
Inputs: monitorId (required).
create_semantic_monitorCreate a semantic monitorAInspect
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.
Inputs: url (required), label, intent, schedule, +1 more.
find_elementsFind interactive elementsAInspect
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.
Inputs: url (required), width, height, dismissCookies.
get_monitor_changesGet monitor change historyBInspect
Returns the recent check history for a monitor, including detected changes with their relevance and explanation.
Inputs: monitorId (required), limit.
list_monitorsList monitorsBInspect
Lists your active monitors and their IDs, URLs and schedules.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Desktop and mobile website screenshots plus page context for AI agents and automation workflows.
Let your AI watch web pages, alert you to changes, and show what any page said on any past date.
Turn the web into structured, reliable, actionable enterprise data for AI Agents
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to see, analyze, and visually verify web page changes through pixel-perfect diffing, theme extraction, layout analysis, and interactive element detection.MIT
- AlicenseAqualityBmaintenanceGives AI agents a compact, semantic interface to the browser, returning structured page snapshots with stable element IDs instead of raw DOM. Enables agents to navigate, interact, and extract information from web pages efficiently.2613 npm19MIT
- AlicenseNot gradedqualityAmaintenanceGives AI agents structured, token-efficient access to the web by returning compact page summaries and targeted queries instead of full accessibility-tree dumps, with tools for navigation, interaction, monitoring, and session management. Agents can drill into detail only when needed, cutting context costs dramatically on content-heavy pages.4 npmMIT
- AlicenseAqualityCmaintenanceGive AI agents eyes on any web page: pixel-perfect screenshots, print-ready PDFs, branded OG images, code images, and structured page extraction (JSON or Markdown).722 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.