IconSaga MCP server
com.iconsaga/iconsiconsaga.comstreamable-httpv1.0.0Scanned
Icons that match, in your colors. Your AI finds them for your website or slides, in 10 languages.
4 tools: 2 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 IconSaga MCP server can do
The IconSaga MCP server is published by iconsaga.com, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: get_icon and match_icons), but cannot delete data. 2 tools only read.
1 tool reads private data (get_icon); 1 tool brings in text other people can write (get_icon).
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 16, 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.
4 tools
Changes things 2Claude Code: ask
get_iconSVG of one icon in a style, two colours and a stroke weight, and code to save in a project: code "tsx" (default) is a React component (size, className and title props; main colour …Reads private dataReads text others write1 finding
Why it is in this group
- The name "get_icon" says "get": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- private-dataThe description's first sentence says "file": it reads files.
- untrusted-inputThe description's first sentence says "html": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "get_icon" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_icon" says "get": a word for reading.
Description, as the server wrote it SVG of one icon in a style, two colours and a stroke weight, and code to save in a project: code "tsx" (default) is a React component (size, className and title props; main colour currentColor so text colour classes work; accent from the CSS variable --icon-accent), "html" an inline SVG snippet, "svg" the file only. format "svg" is a still icon (1-2 filled paths, works in PowerPoint, Figma, web); "anim-svg" plays its motion in browsers with no player or script.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
match_iconsMany icon names at once, as a project's UI icon set writes them (arrow-right, circle-check, shopping-cart, trash-2, HomeIcon), each with the closest IconSaga icon: to swap the icon…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Many icon names at once, as a project's UI icon set writes them (arrow-right, circle-check, shopping-cart, trash-2, HomeIcon), each with the closest IconSaga icon: to swap the icons of a whole project in one call. match is "name" (a known name), "search" (found by meaning) or "none". Then get_icon for the code of each.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
list_setsAll icon sets with how many icons each has.No findings
Why it is in this group
- The name "list_sets" says "list": a word for reading.
Description, as the server wrote it All icon sets with how many icons each has.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_iconsSearch IconSaga icons by meaning, in the user's own language (English, Thai, Spanish, Portuguese, French, German, Japanese, Chinese, Korean, Indonesian or mixed).No findings
Why it is in this group
- The name "search_icons" says "search": a word for reading.
Description, as the server wrote it Search IconSaga icons by meaning, in the user's own language (English, Thai, Spanish, Portuguese, French, German, Japanese, Chinese, Korean, Indonesian or mixed). Also takes an icon name as UI icon sets write it (arrow-right, circle-check, shopping-cart, trash-2, HomeIcon) and returns the matching icon first. Returns icon ids, labels, versions, styles and licence per icon.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 write1
- 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.
Looked at Nov 17, 2026, 15:18 UTC, unchanged since Nov 17, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://iconsaga.com/mcp: tools/list returned 4 tools to an anonymous client, including get_icon (write), match_icons (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnget_icon
The server marks "get_icon" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "get_icon" says "get": a word for reading.
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 icons https://iconsaga.com/mcpclaude mcp add --transport http icons https://iconsaga.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__icons__search_icons",
"mcp__icons__list_sets"
],
"ask": [
"mcp__icons__get_icon",
"mcp__icons__match_icons"
],
"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 icons. Review it before you use it.
Capability tags behind 1 rule
- mcp__icons__get_icon private-data, 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/com.iconsaga/icons/verify?hash=56061139aa4eb2a194991f8ed1438b7eb48d58093bf4a185910fe0a1c31ed3bf" | jq -e '.changed == false'Pinned hash 56061139aa4e, from Nov 16, 2026, 16:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.iconsaga/icons/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.iconsaga/icons)Source: MCP Registry · repository. Synced Nov 16, 2026, 16:17 UTC.
IconSaga MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the IconSaga MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 2 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 IconSaga MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the IconSaga 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 IconSaga MCP server have?
- 4 tools: 2 write, 2 read. get_icon, match_icons, search_icons and list_sets.
Does the IconSaga MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the IconSaga MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the IconSaga MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.