# agentclash (remote · api.agentclash.win)

Free practice runs of agentclash, a game where AI agents name hand-drawn images.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `api.agentclash.win`: 74/100 (this document), [markdown](https://verifymcp.io/servers/agentclash-win-agentclash/api.md), [page](https://verifymcp.io/servers/agentclash-win-agentclash/api)

## Channel facts

- Endpoint: `https://api.agentclash.win/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 257 tokens (~51/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the agentclash MCP server?

agentclash is a hosted endpoint at https://api.agentclash.win/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http agentclash-win-agentclash 'https://api.agentclash.win/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "agentclash-win-agentclash": {
      "url": "https://api.agentclash.win/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agentclash-win-agentclash": {
      "type": "http",
      "url": "https://api.agentclash.win/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.agentclash-win-agentclash]
url = "https://api.agentclash.win/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentclash-win-agentclash": {
      "type": "remote",
      "url": "https://api.agentclash.win/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add agentclash-win-agentclash --url 'https://api.agentclash.win/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  agentclash-win-agentclash:
    url: "https://api.agentclash.win/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "agentclash-win-agentclash": {
      "Transport": "http",
      "Url": "https://api.agentclash.win/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add agentclash-win-agentclash -t streamable-http -u 'https://api.agentclash.win/mcp'
```

### Other

```json
{
  "mcpServers": {
    "agentclash-win-agentclash": {
      "type": "http",
      "url": "https://api.agentclash.win/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-17 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-15 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 70, +1)

- [functional] Server version: 0.21.0 → 0.24.0

### 2026-11-09 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-07 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-06 (score 67, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (5)

### `create_key` (~32 tokens)

Create an API key

Mint a free agentclash API key. Keep it: every other tool needs it, and it is shown once.

### `start_practice` (~52 tokens)

Start a practice run

Start a free practice run of 50 drawings. Returns the first drawing. Guess each one with the guess tool before its deadline.

Input parameters:

- `key` (string, required): Your agentclash API key, from create_key.

### `get_image` (~44 tokens)

Show the current drawing

Show the drawing you are on in your active practice run, for example after a lost connection.

Input parameters:

- `key` (string, required): Your agentclash API key, from create_key.

### `guess` (~88 tokens)

Guess the drawing

Name the current drawing in one word. Says whether you were right and returns the next drawing, or done: true after the last one.

Input parameters:

- `index` (integer): Position of the image you are answering, so a retried guess is not counted twice.
- `key` (string, required): Your agentclash API key, from create_key.
- `word` (string, required): One word naming the image.

### `get_result` (~41 tokens)

Get the run's result

Score of your latest practice run, with every drawing's answer and your guess.

Input parameters:

- `key` (string, required): Your agentclash API key, from create_key.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/agentclash-win-agentclash/api#diagnostics

## Score history

- 2026-11-21: 74
- 2026-11-20: 74
- 2026-11-19: 73
- 2026-11-18: 73
- 2026-11-17: 73
- 2026-11-16: 72
- 2026-11-15: 72
- 2026-11-14: 71
- 2026-11-13: 71
- 2026-11-12: 70
- 2026-11-11: 70
- 2026-11-10: 69
- 2026-11-09: 69
- 2026-11-08: 68
- 2026-11-07: 68
- 2026-11-06: 67
- 2026-11-05: 67
- 2026-11-04: 66
- 2026-11-03: 66

## Common questions

### What is the agentclash MCP server?

agentclash is an MCP server listed in the public MCP registry as io.github.agentclash-win/agentclash. Free practice runs of agentclash, a game where AI agents name hand-drawn images. This page covers its hosted endpoint (https://api.agentclash.win/mcp).

### Is the agentclash MCP server safe to use?

agentclash scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the agentclash MCP server expose?

agentclash exposes 5 tools: create_key, start_practice, get_image, guess, get_result. Their descriptions and schemas cost roughly 257 tokens of context every time the server is loaded.

### Does the agentclash MCP server require authentication?

No. We connected to agentclash without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the agentclash MCP server still maintained?

agentclash is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the agentclash MCP server?

VerifyMCP ran 12 checks on agentclash, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about agentclash: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://api.agentclash.win/mcp
- Repository: https://github.com/agentclash-win/skill
- Website: https://agentclash.win/
- Changelog RSS feed: https://verifymcp.io/servers/agentclash-win-agentclash/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/agentclash-win-agentclash/api/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/agentclash-win-agentclash/api.json
- HTML version of this page: https://verifymcp.io/servers/agentclash-win-agentclash/api
