# `io.github.RafaCoelho33/web3-systemic-agent` 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/io.github.RafaCoelho33/web3-systemic-agent
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.RafaCoelho33/web3-systemic-agent
- Version: 1.0.1 (active)
- Publisher: io.github.RafaCoelho33 (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/RafaCoelho33/web3-systemic-agent
- Metadata from the official MCP Registry, synced 2026-11-11T23:17:38.908Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Web3 Systemic Agent
Web3 security & DAO auditor: free bytecode/honeypot/Snapshot tools + x402 Gemini LLM deep audit.
```

Scanned 2026-11-11T23:18:24.410Z over streamable-http.

**4 tools: 4 change things.**

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

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data 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. | `mcp__web3-systemic-agent__check_token_honeypot` `mcp__web3-systemic-agent__deep_semantic_audit` `mcp__web3-systemic-agent__scan_contract_selectors` `mcp__web3-systemic-agent__scan_dao_proposals` |
| 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.


## Changes things (4)

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

### `check_token_honeypot`

- 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.
- 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
Stage 1 Free static bytecode scanner for honeypot indicators on DEX tokens: blacklist manipulation (isBlacklisted, setBlacklist), arbitrary transfer taxes / 100% sell fee traps, trading freeze backdoors, and selfdestruct opcodes.
```

### `deep_semantic_audit`

- 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.
- 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
Stage 2 Deep Semantic LLM Security and Governance Audit. Performs deterministic on-chain gatekeeping followed by structured Gemini LLM evaluation over natural language proposal claims vs bytecode and calldata reality. Requires $0.05 USDC x402 micropayment on Base Mainnet.
```

### `scan_contract_selectors`

- 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.
- 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
Stage 1 Free deterministic inspection of smart contract bytecode on Base or EVM chains. Discovers 4-byte function selectors and flags high-risk administrative capabilities (ownership transfer, proxy upgrade, unconstrained minting, selfdestruct).
```

### `scan_dao_proposals`

- 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.
- 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
Stage 1 Free scanner for recent Snapshot DAO governance proposals (Arbitrum, Aave, ENS). Extracts on-chain target addresses and calldata execution payloads to detect governance takeover attempts and discrepancies.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `web3-systemic-agent`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__web3-systemic-agent__scan_contract_selectors",
      "mcp__web3-systemic-agent__check_token_honeypot",
      "mcp__web3-systemic-agent__scan_dao_proposals",
      "mcp__web3-systemic-agent__deep_semantic_audit"
    ],
    "deny": []
  }
}
```

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

- `mcp__web3-systemic-agent__scan_contract_selectors`: untrusted-input
- `mcp__web3-systemic-agent__check_token_honeypot`: untrusted-input
- `mcp__web3-systemic-agent__scan_dao_proposals`: untrusted-input
- `mcp__web3-systemic-agent__deep_semantic_audit`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-16T14:21:08.090Z, unchanged since 2026-11-09T07:19:19.989Z. 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 | `4` |
| Protocol version | `2024-11-05` |
| 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://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

https://web3-systemic-agent.onrender.com/mcp: tools/list returned 4 tools to an anonymous client, including scan_contract_selectors (write), check_token_honeypot (write), scan_dao_proposals (write), deep_semantic_audit (write)
```
