# `io.github.sacrosaunt/redra` 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.sacrosaunt/redra
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.sacrosaunt/redra
- Version: 0.1.0 (active)
- Publisher: io.github.sacrosaunt (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/sacrosaunt/Redra
- Metadata from the official MCP Registry, synced 2026-10-21T18:46:33.237Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Redra
Search current class-action settlements and identify possible matches using structured filters.
```

Scanned 2026-11-20T11:17:51.992Z over streamable-http.

**5 tools: 1 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 | 1 | 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

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

```untrusted-server-text
The server marks "search_settlements_batch" 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 "search_settlements_batch" says "search": a word for reading.
```


## Changes things (1)

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

### `search_settlements_batch`

- The name "search_settlements_batch" says "search": a word for reading.
- 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 up to 50 independent settlement searches and deduplicate records across queries. Results include matched_query_indices, and executed_query_count reports the number of searches performed. Use when several unrelated search angles should be evaluated together.
```

## Only reads (4)

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

### `get_dataset_info`

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

Description, as the server wrote it:

```untrusted-server-text
Return source, license, freshness, counts, and hosted aggregate metrics.
```

### `get_settlement`

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

Description, as the server wrote it:

```untrusted-server-text
Return the complete stored record and official source links for one settlement ID produced by a search.
```

### `get_settlements`

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

Description, as the server wrote it:

```untrusted-server-text
Return complete stored records and official source links for up to 20 settlement IDs produced by search.
```

### `search_settlements`

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

Description, as the server wrote it:

```untrusted-server-text
Search one settlement angle using logical AND keywords and structured status, type, state, proof, and deadline filters. Status defaults to open. Results include source metadata and quality flags.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__redra__search_settlements",
      "mcp__redra__get_settlement",
      "mcp__redra__get_settlements",
      "mcp__redra__get_dataset_info"
    ],
    "ask": [
      "mcp__redra__search_settlements_batch"
    ],
    "deny": []
  }
}
```

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:10:33.235Z, unchanged since 2026-10-22T15:05:05.888Z. 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` |

- **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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

https://mcp.redra.ai/mcp: tools/list returned 5 tools to an anonymous client, including search_settlements_batch (write)
```
