CaptureOneAI Web Perception MCP server
com.captureoneai/web-perceptioncaptureoneai.comstreamable-httpv1.0.0Scanned
Give agents eyes on any web page: structured context, and changes explained in plain language.
6 tools: 1 do something that can't be undone, 2 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the CaptureOneAI Web Perception MCP server can do
The CaptureOneAI Web Perception MCP server is published by captureoneai.com, a domain the MCP Registry verified. It has 6 tools. It can do things that cannot be undone, such as sending, paying or publishing (capture_context) and create or change data (2 tools: create_semantic_monitor and check_monitor), but cannot delete data. 3 tools only read.
1 tool brings in text other people can write (find_elements); 3 tools can send data out of your system (capture_context, find_elements and create_semantic_monitor).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Can't be undone 1Claude Code: ask
capture_contextReturns the structured representation of a web page: visible text with coordinates, interactive elements, forms and tables.Can send data outNo findings
Why it is in this group
- The name "capture_context" says "capture": a word that usually means money moves, which cannot be taken back.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Changes things 2Claude Code: ask
check_monitorTriggers an immediate check for a monitor instead of waiting for its next scheduled run, and returns any detected changes.No findings
Why it is in this group
- The description's first verb is "trigger": a word for a change.
Description, as the server wrote it Triggers an immediate check for a monitor instead of waiting for its next scheduled run, and returns any detected changes.
create_semantic_monitorWatches a URL on a schedule and reports what changed and whether it matters, explained by AI — not just a pixel-diff percentage.Can send data outNo findings
Why it is in this group
- The name "create_semantic_monitor" says "create": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Only reads 3Show 3 read-only tools
find_elementsReturns only the interactive elements of a page (buttons, links, inputs) with role, label, CSS selector and pixel coordinates.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "find_elements" says "find": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
get_monitor_changesReturns the recent check history for a monitor, including detected changes with their relevance and explanation.No findings
Why it is in this group
- The name "get_monitor_changes" says "get": a word for reading.
Description, as the server wrote it Returns the recent check history for a monitor, including detected changes with their relevance and explanation.
list_monitorsLists your active monitors and their IDs, URLs and schedules.No findings
Why it is in this group
- The name "list_monitors" says "list": a word for reading.
Description, as the server wrote it Lists your active monitors and their IDs, URLs and schedules.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:35 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://captureoneai.com/mcp: tools/list returned 6 tools to an anonymous client, including capture_context (irreversible), create_semantic_monitor (write), check_monitor (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http web-perception https://captureoneai.com/mcpclaude mcp add --transport http web-perception https://captureoneai.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__web-perception__list_monitors",
"mcp__web-perception__get_monitor_changes"
],
"ask": [
"mcp__web-perception__capture_context",
"mcp__web-perception__find_elements",
"mcp__web-perception__create_semantic_monitor",
"mcp__web-perception__check_monitor"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as web-perception. Review it before you use it.
Capability tags behind 3 rules
- mcp__web-perception__capture_context outbound
- mcp__web-perception__find_elements untrusted-input, outbound
- mcp__web-perception__create_semantic_monitor outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.captureoneai/web-perception/verify?hash=233963ec1d209f5be89a62067389acc5a665787b1dc11d780405f5e2ed7381dc" | jq -e '.changed == false'Pinned hash 233963ec1d20, from Nov 10, 2026, 12:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.captureoneai/web-perception/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.captureoneai/web-perception)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:52 UTC.
CaptureOneAI Web Perception MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the CaptureOneAI Web Perception MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the CaptureOneAI Web Perception MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the CaptureOneAI Web Perception MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: capture_context.
What tools does the CaptureOneAI Web Perception MCP server have?
- 6 tools: 1 irreversible, 2 write, 3 read. capture_context, create_semantic_monitor, check_monitor, find_elements, list_monitors and get_monitor_changes.
Does the CaptureOneAI Web Perception MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the CaptureOneAI Web Perception MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): capture_context, find_elements and create_semantic_monitor.
Has the CaptureOneAI Web Perception MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.