# `io.github.SolDevelo/infrascan-cloud` 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.SolDevelo/infrascan-cloud
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.SolDevelo/infrascan-cloud
- Version: 1.0.2 (active)
- Publisher: io.github.SolDevelo (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-20T19:17:43.243Z

Title and description, as the publisher wrote them:

```untrusted-server-text
InfraScan Cloud
Read-only AWS cost and security findings, priced in $/month, with a fix for each
```

Scanned 2026-11-20T19:17:57.207Z over streamable-http.

**4 tools: 1 change things and 3 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 3 | allow |

## Exfil surface

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

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__infrascan-cloud__get_finding` `mcp__infrascan-cloud__get_scan_summary` `mcp__infrascan-cloud__list_findings` `mcp__infrascan-cloud__list_targets` |
| 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 `list_targets` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "list_targets" 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 name "list_targets" says "list": a word for reading.
```


## Changes things (1)

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

### `list_targets`

- The name "list_targets" says "list": a word for reading.
- The description's first verb is "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag private-data: The description's first sentence says "repository": it reads repositories.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Start here: every AWS account and repository this organization scans, with its ID and a one-line status from its latest completed scan (grades A–F, open findings by severity, potential monthly savings), to pick one. Pass an ID to list_findings or get_scan_summary; for one target's details, use get_scan_summary.
```

## Only reads (3)

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

### `get_finding`

- The name "get_finding" says "get": a word for reading.
- Tag private-data: The description's first sentence says "repository": it reads repositories.

Description, as the server wrote it:

```untrusted-server-text
One finding in full: what and where (AWS resource ARN and region, or repository, file, line and IaC resource), why it matters, the evidence, how to fix it (console steps, an AWS CLI command and Terraform where we have them), references, and whether its risk was accepted or it was marked as fixed. The fix is a suggestion: check that the finding still applies before changing anything.
```

### `get_scan_summary`

- The name "get_scan_summary" says "get": a word for reading.
- Tag private-data: The description's first sentence says "repository": it reads repositories.

Description, as the server wrote it:

```untrusted-server-text
One AWS account's or repository's latest completed scan in detail (a target_id from list_targets): when it ran, why each grade is capped, findings by severity and by pillar, potential monthly savings, and what changed since the scan before it (new findings, resolved ones and the monthly cost they saved).
```

### `list_findings`

- The name "list_findings" says "list": a word for reading.
- Tag private-data: The description's first sentence says "repository": it reads repositories.

Description, as the server wrote it:

```untrusted-server-text
Findings from the latest completed scan of every AWS account and repository (or of one target), most severe first, then by monthly savings. Each row is short; call get_finding with its id for the description, evidence and fix. Repository findings name the file and line; AWS findings name the resource and region. By default only open findings are listed (including ones someone marked as fixed that the next scan has yet to verify).
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__infrascan-cloud__list_findings",
      "mcp__infrascan-cloud__get_finding",
      "mcp__infrascan-cloud__get_scan_summary"
    ],
    "ask": [
      "mcp__infrascan-cloud__list_targets"
    ],
    "deny": []
  }
}
```

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

- `mcp__infrascan-cloud__list_targets`: private-data
- `mcp__infrascan-cloud__list_findings`: private-data
- `mcp__infrascan-cloud__get_finding`: private-data
- `mcp__infrascan-cloud__get_scan_summary`: private-data

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-18T16:19:43.513Z, unchanged since 2026-11-18T16:19:43.513Z. 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 | `0` |
| 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` |
