agentclash MCP server
io.github.agentclash-win/agentclashagentclash-winstreamable-httpv0.0.1Scanned
Free practice runs of agentclash, a game where AI agents name hand-drawn images.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 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 agentclash MCP server can do
The agentclash MCP server is published by the GitHub account agentclash-win. It has 5 tools. It can create or change data (3 tools: create_key, start_practice and guess), but cannot delete data. 2 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (tool-shadowing). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.0.1.
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.
5 tools
Changes things 3Claude Code: ask
create_keyMint a free agentclash API key.1 finding
Why it is in this group
- The name "create_key" says "create": a word for a change.
Findings
- Warn
The description contains "every other tool", wording about other tools or servers.
What this check looks forMatched text
description: "...int a free agentclash API key. Keep it: every other tool needs it, and it is shown once."
Description, as the server wrote it Mint a free agentclash API key. Keep it: every other tool needs it, and it is shown once.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
guessName the current drawing in one word.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.
Description, as the server wrote it Name the current drawing in one word. Says whether you were right and returns the next drawing, or done: true after the last one.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
start_practiceStart a free practice run of 50 drawings.No findings
Why it is in this group
- The name "start_practice" says "start": a word for a change.
Description, as the server wrote it Start a free practice run of 50 drawings. Returns the first drawing. Guess each one with the guess tool before its deadline.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
Only reads 2Show 2 read-only tools
get_imageShow the drawing you are on in your active practice run, for example after a lost connection.No findings
Why it is in this group
- The name "get_image" says "get": a word for reading.
Description, as the server wrote it Show the drawing you are on in your active practice run, for example after a lost connection.
Annotations the server declares
- readOnlyHint: true
get_resultScore of your latest practice run, with every drawing's answer and your guess.No findings
Why it is in this group
- The name "get_result" says "get": a word for reading.
Description, as the server wrote it Score of your latest practice run, with every drawing's answer and your guess.
Annotations the server declares
- readOnlyHint: 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 private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 18, 2026, 16:22 UTC, unchanged since Nov 4, 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.agentclash.win/mcp: tools/list returned 5 tools to an anonymous client, including create_key (write), start_practice (write), guess (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncreate_key
The description contains "every other tool", wording about other tools or servers.
What this check looks forMatched text
description: "...int a free agentclash API key. Keep it: every other tool needs it, and it is shown once."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:guessChanges thingsannotations
- Changed:start_practiceChanges thingsannotations
Install
Pinned to version 0.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentclash https://api.agentclash.win/mcpclaude mcp add --transport http agentclash https://api.agentclash.win/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__agentclash__get_image",
"mcp__agentclash__get_result"
],
"ask": [
"mcp__agentclash__create_key",
"mcp__agentclash__start_practice",
"mcp__agentclash__guess"
],
"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 agentclash. Review it before you use it.
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/io.github.agentclash-win/agentclash/verify?hash=681a9c9036330bee5a36c5c83d8842f39cb1fc9f881130fcdf561c9a302d2cb1" | jq -e '.changed == false'Pinned hash 681a9c903633, from Nov 16, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.agentclash-win/agentclash/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.agentclash-win/agentclash)Source: MCP Registry · repository. Synced Nov 3, 2026, 10:17 UTC.
agentclash MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agentclash MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 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 agentclash MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the agentclash 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 agentclash MCP server have?
- 5 tools: 3 write, 2 read. create_key, start_practice, guess, get_image and get_result.
Does the agentclash MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the agentclash MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the agentclash MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.