# `com.deepcounterfeit/deepcounterfeit` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://anlyon.dev/servers/com.deepcounterfeit/deepcounterfeit
- JSON: https://anlyon.dev/api/v1/servers/com.deepcounterfeit/deepcounterfeit
- Version: 1.0.0 (active)
- Publisher: com.deepcounterfeit (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:54:07.977Z

Title and description, as the publisher wrote them:

```untrusted-server-text
DeepCounterfeit
Flags memecoins impersonating real brands, official tokens and tokenized stocks. Read-only.
```

Scanned 2026-10-21T18:48:14.656Z over streamable-http.

**8 tools: 2 change things and 6 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | ask |
| Only reads | read | 6 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | none |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

- **warn** Annotations that disagree with the tool in `check_name` ([annotation-conflict](https://anlyon.dev/methodology#annotation-conflict))

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

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.
```


## Changes things (2)

Creates or changes something that can be changed back. Claude Code: ask.

### `check_name`

- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Run the impersonation detector on a token name and/or ticker symbol without needing an address. Tells you whether a coin called e.g. "SpaceX Official" ($SPACEX) or "TSLAx" would be flagged as impersonating a brand, which brand, and why. Use for pre-launch name checks, or when a user mentions a coin by name and you have no address (with an address, use check_token). Does not assess creator behaviour.
```

### `check_token`

- 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:

```untrusted-server-text
Look up a deployed token by contract/mint address and report whether it impersonates a real company, its "official" token or its tokenized stock (e.g. a fake SpaceX, Coinbase or NVDAx coin). Returns verdict (likely_impersonation | brand_mention_watch | not_in_index), matched brands, risk score 0-100 with reasons (creator bought supply at launch, same-block bundles, creator cash-out, serial launcher), creator wallet and explorer links. Use before buying, listing or promoting a token. "not_in_index" only means no brand match was recorded, not that the token is safe. Without an API key: brand match and coin only (flagged as likely impersonation), no risk score, creator wallet or forensics.
```

## Only reads (6)

Looks things up and changes nothing. Claude Code: allow.

### `fetch`

- The name "fetch" says "fetch": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Fetch the full check_token result for a result id returned by search (format "<chain>:<address>"): verdict, matched brands, match type and explorer links; with an API key also risk score, reasons and creator facts. Use after search; for a known address call check_token directly.
```

### `get_brand_report`

- The name "get_brand_report" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Summarise impersonation activity against one brand over a window: number of fake coins, traded volume, breakdown by chain/match type/severity, repeat creator wallets, how many creators bought 50%+ of supply, and the top cases with evidence. Pro/Wholesale keys also get the takedown-ready PDF link.
```

### `get_stats`

- The name "get_stats" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Aggregate numbers for a window: alerts, high-severity count, brands hit, by chain, by match type, top brands, data-source health and coverage. Use for overviews, trend questions and to check data freshness.
```

### `list_brands`

- The name "list_brands" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List the brands on the watchlist (companies, tokenized stocks, crypto projects, private companies) with ids, tickers and all-time alert counts, most-targeted first. Use to find a brand id or check whether a brand is covered.
```

### `search`

- The name "search" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Search the impersonation index by brand name, ticker or coin name. Returns result ids for fetch. Prefer search_alerts / check_name when available.
```

### `search_alerts`

- The name "search_alerts" says "search": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List recent impersonation coins, newest first, filtered by brand, chain, time and severity. Use to answer "are there fake <brand> tokens?", to monitor a brand, or to collect cases for a takedown. Free tier returns alerts older than 24 h only (max 20).
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `deepcounterfeit`:

```json
{
  "permissions": {
    "allow": [
      "mcp__deepcounterfeit__search_alerts",
      "mcp__deepcounterfeit__get_brand_report",
      "mcp__deepcounterfeit__list_brands",
      "mcp__deepcounterfeit__get_stats",
      "mcp__deepcounterfeit__search",
      "mcp__deepcounterfeit__fetch"
    ],
    "ask": [
      "mcp__deepcounterfeit__check_token",
      "mcp__deepcounterfeit__check_name"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T14:30:34.823Z, unchanged since 2026-10-22T14:30:34.823Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| 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 | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
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.

https://deepcounterfeit.com/mcp: tools/list returned 8 tools to an anonymous client, including check_token (write), check_name (write)
```