# `io.tooloracle/riskoracle` 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.tooloracle/riskoracle
- JSON: https://radar.anlyon.com/api/v1/servers/io.tooloracle/riskoracle
- Version: 1.0.0 (active)
- Publisher: io.tooloracle (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/ToolOracle/riskoracle
- Metadata from the official MCP Registry, synced 2026-10-21T18:52:51.714Z

Title and description, as the publisher wrote them:

```untrusted-server-text
RiskOracle - 13-tool enterprise risk MCP: heatmaps, KRIs, scenario sims, Basel/ICAAP outputs.
```

Scanned 2026-11-21T17:18:04.717Z over streamable-http.

**13 tools: 9 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 9 | ask |
| Only reads | read | 4 | 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

No check matched anything in these tool definitions.


## Changes things (9)

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

### `cross_chain_data`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Cross-chain distribution, bridge risk
```

### `custody_data`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Custody model, SIFI status, jurisdiction
```

### `holder_data`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Top holder distribution, whale concentration
```

### `leaderboard`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Stablecoins ranked by risk score
```

### `methodology`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Risk scoring methodology
```

### `peg_history`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
30-day peg history
```

### `redemption_data`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Redemption track record, latency, limits
```

### `risk_assessment`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Full risk score — 7 signals, 100-point scale, SAFE/CAUTION/AVOID
```

### `supply_flow`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Supply minting/burning, net flow
```

## Only reads (4)

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

### `compare`

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

Description, as the server wrote it:

```untrusted-server-text
Head-to-head comparison of 2+ stablecoins
```

### `peg_status`

- The name "peg_status" says "status": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Current peg status — deviation, stability
```

### `ping`

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

Description, as the server wrote it:

```untrusted-server-text
Server ping
```

### `supported_tokens`

- The description's first verb is "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
List supported stablecoins
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__riskoracle__ping",
      "mcp__riskoracle__peg_status",
      "mcp__riskoracle__compare",
      "mcp__riskoracle__supported_tokens"
    ],
    "ask": [
      "mcp__riskoracle__risk_assessment",
      "mcp__riskoracle__peg_history",
      "mcp__riskoracle__supply_flow",
      "mcp__riskoracle__holder_data",
      "mcp__riskoracle__custody_data",
      "mcp__riskoracle__redemption_data",
      "mcp__riskoracle__cross_chain_data",
      "mcp__riskoracle__leaderboard",
      "mcp__riskoracle__methodology"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:31:55.782Z, unchanged since 2026-10-22T15:25:58.481Z. 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 | `9` |
| Protocol version | `2025-03-26` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `https://tooloracle.io/.well-known/oauth-protected-resource/risk/mcp` |
| Authorization servers | `https://feedoracle.io` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `yes` |
| Client ID metadata documents | `no` |

- **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 9 tools that change things (9 write). Whether a call also works without credentials was not tested: tools are never called.

https://tooloracle.io/risk/mcp/: tools/list returned 13 tools to an anonymous client, including risk_assessment (write), peg_history (write), supply_flow (write), holder_data (write), custody_data (write) and 4 more
```
