Skip to content

Icon Horse MCP server

horse.icon/icon-horseicon.horsestreamable-httpv2.0.0Scanned

Logos and favicons for any domain or product name, with confidence scores. Free, no key.

4 tools: 1 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 1 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 4
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Icon Horse MCP server can do

The Icon Horse MCP server is published by icon.horse, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: logo_set), but cannot delete data. 3 tools only read.

1 tool reads private data (company_stack); 4 tools bring in text other people can write (find_logos, get_logo_image, company_stack and 1 more).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 2026, version 2.0.0.

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.

4 tools

Changes things 1Claude Code: ask
  • logo_setReturn logos as a matched set for one background and size: same visual weight and padding, full color or one tone, with warnings when a logo will not read on the background.Reads text others write1 finding

    Why it is in this group

    • The name "logo_set" says "set": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "logo_set" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "logo_set" says "set": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Return logos as a matched set for one background and size: same visual weight and padding, full color or one tone, with warnings when a logo will not read on the background. Missing logos become neutral stand-in tiles marked standIn: true. Includes a row_url that renders the whole set as one PNG strip.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • company_stackFind which tools a company uses (client portals, practice software, email, CRM, analytics), from its website and DNS.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The description's first verb is "find": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "find" and "email": it reads mail.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "find" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Find which tools a company uses (client portals, practice software, email, CRM, analytics), from its website and DNS. Every tool comes with the evidence that was observed and a confidence. Absence of a tool means no evidence was found, not that the company does not use it.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • find_logosLook up logos for domains or product names.Reads text others writeNo findings

    Why it is in this group

    • The name "find_logos" says "find": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Look up logos for domains or product names. Returns, per query: found/fallback, confidence (0 = placeholder), name, source URL and size, and public PNG/WebP/ICO/SVG URLs.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_logo_imageReturn one logo as an image you can look at, plus its URL.Reads text others writeNo findings

    Why it is in this group

    • The name "get_logo_image" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Return one logo as an image you can look at, plus its URL. Use to check a logo before placing it. Options: size (16-256), bg (hex, white, black), pad (0-40 percent), trim.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

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 outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:21 UTC, unchanged since Nov 14, 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
1
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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://icon.horse/mcp: tools/list returned 4 tools to an anonymous client, including logo_set (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "logo_set" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "logo_set" says "set": a word for a change.

    What this check looks for

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 2.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http icon-horse https://icon.horse/mcp
claude mcp add --transport http icon-horse https://icon.horse/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__icon-horse__find_logos",
      "mcp__icon-horse__get_logo_image",
      "mcp__icon-horse__company_stack"
    ],
    "ask": [
      "mcp__icon-horse__logo_set"
    ],
    "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 icon-horse. Review it before you use it.

Capability tags behind 4 rules
  • mcp__icon-horse__find_logos untrusted-input
  • mcp__icon-horse__get_logo_image untrusted-input
  • mcp__icon-horse__company_stack private-data, untrusted-input
  • mcp__icon-horse__logo_set untrusted-input

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/horse.icon/icon-horse/verify?hash=203e2d6d5a20377cc2d09b069d1f49d31a71c83de7a3f63351566da28829f41c" | jq -e '.changed == false'

Pinned hash 203e2d6d5a20, from Nov 13, 2026, 22:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/horse.icon/icon-horse/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for horse.icon/icon-horse
[![Anlyon Radar](https://radar.anlyon.com/badge/horse.icon/icon-horse.svg)](https://radar.anlyon.com/servers/horse.icon/icon-horse)

Source: MCP Registry. Synced Nov 13, 2026, 22:17 UTC.

Icon Horse MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Icon Horse MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Icon Horse MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Icon Horse MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Icon Horse MCP server have?

4 tools: 1 write, 3 read. logo_set, find_logos, get_logo_image and company_stack.

Does the Icon Horse MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Icon Horse MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Icon Horse MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.