# `software.brainiac/crypto-security` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. 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://radar.anlyon.com/servers/software.brainiac/crypto-security
- JSON: https://radar.anlyon.com/api/v1/servers/software.brainiac/crypto-security
- Version: 1.0.1 (active)
- Publisher: software.brainiac (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-20T01:18:20.821Z

Title and description, as the publisher wrote them:

```untrusted-server-text
BRAINIAC Crypto Security
Paid Crypto Security API via x402. Unpaid tool calls return 402.
```

Scanned 2026-11-20T01:19:49.985Z over streamable-http.

**4 tools: 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

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

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__crypto-security__crypto-security_intent-safety` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__crypto-security__crypto-security_intent-safety` `mcp__crypto-security__crypto-security_proxy-upgrade-storage-audit` `mcp__crypto-security__crypto-security_storage-slot-grade` `mcp__crypto-security__crypto-security_transaction-intent-verify` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Only reads (4)

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

### `crypto-security_intent-safety`

- The description's first verb is "read": a word for reading.
- Tag private-data: The description's first sentence says "read" and "message": it reads messages.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "read" and "message": it reads messages, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Read a caller-supplied EVM transaction or an EIP-712 typed-data message and describe the transfer, approval, permit, or outer call it encodes. Known selectors are transfer, transferFrom, approve, increaseAllowance, setApprovalForAll, permit, multicall, aggregate, and execute. The score is a local penalty count. It does not simulate the call or read a chain. Price $0.04 USDC. POST /api/v1/crypto-security/intent-safety. An unpaid call returns the x402 payment terms and does not run.
```

### `crypto-security_proxy-upgrade-storage-audit`

- The description's first verb is "compare": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Compare the Solidity storage layout of an upgradeable implementation with a proposed replacement. Variables are matched by slot and offset, not by name. The types map is used for structs, mappings, dynamic arrays, and byte sizes. compatibility_status is compatible, incompatible, warnings, or indeterminate. risk_level is low, medium, high, or critical. A compatible result is not a claim that the upgrade is safe. No chain is queried. Price $0.05 USDC. POST /api/v1/crypto-security/proxy-upgrade-storage-audit. An unpaid call returns the x402 payment terms and does not run.
```

### `crypto-security_storage-slot-grade`

- The description's first verb is "compare": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Compare two caller-supplied storage layouts by slot, offset, and size. A name that moves is a shift. Different names that occupy the same bytes are a collision. The grade and the collision score come from those counts. A variable is one slice of a single slot. No chain is queried. Price $0.04 USDC. POST /api/v1/crypto-security/storage-slot-grade. An unpaid call returns the x402 payment terms and does not run.
```

### `crypto-security_transaction-intent-verify`

- The description's first verb is "compare": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Compare an EVM transaction's calldata and native value with the action declared in the request. Decoding uses the ABI in the request, or the standard ERC-20 transfer, transferFrom, approve, and increaseAllowance encodings when that selector matches. intent_match is true, false, or the string indeterminate when a declared field cannot be checked. risk_level is low, medium, high, or critical. This is static analysis: it does not read chain state, simulate the call, or decide that a contract is malicious or that the transaction will succeed. Price $0.04 USDC. POST /api/v1/crypto-security/transaction-intent-verify. An unpaid call returns the x402 payment terms and does not run.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `crypto-security`:

```json
{
  "permissions": {
    "allow": [
      "mcp__crypto-security__crypto-security_transaction-intent-verify",
      "mcp__crypto-security__crypto-security_intent-safety",
      "mcp__crypto-security__crypto-security_proxy-upgrade-storage-audit",
      "mcp__crypto-security__crypto-security_storage-slot-grade"
    ],
    "ask": [],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__crypto-security__crypto-security_transaction-intent-verify`: untrusted-input
- `mcp__crypto-security__crypto-security_intent-safety`: private-data, untrusted-input
- `mcp__crypto-security__crypto-security_proxy-upgrade-storage-audit`: untrusted-input
- `mcp__crypto-security__crypto-security_storage-slot-grade`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:31:01.671Z, unchanged since 2026-11-20T19:31:01.671Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/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 | `1` |
| 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` |

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

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

https://www.brainiac.software/mcp/crypto-security: tools/list returned 4 tools to an anonymous client, including crypto-security_transaction-intent-verify (irreversible)
```
