# `io.github.burmanharry/cleaningredients` 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.burmanharry/cleaningredients
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.burmanharry/cleaningredients
- Version: 1.0.0 (active)
- Publisher: io.github.burmanharry (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/burmanharry/cleaningredients
- Metadata from the official MCP Registry, synced 2026-11-15T23:17:39.413Z

Title and description, as the publisher wrote them:

```untrusted-server-text
CleanIngredients
Research China-origin botanicals, supplier evidence gaps, sourcing briefs and ingredient costs.
```

Scanned 2026-11-15T23:18:15.657Z over streamable-http.

**7 tools: 2 change things and 5 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 2 | ask |
| Only reads | read | 5 | 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__cleaningredients__search_ingredients` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__cleaningredients__get_evidence_coverage` `mcp__cleaningredients__get_ingredient` |
| 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 `build_sourcing_brief` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "build_sourcing_brief" 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 description's first verb is "generate": a word for a change.
```


## Changes things (2)

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

### `build_sourcing_brief`

- The description's first verb is "generate": 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
Generate an RFQ draft for a catalog ingredient. Returns text only: does not store personal data, submit an inquiry, contact a supplier or place an order. Review the draft before using the website inquiry form.
```

### `calculate_landed_cost`

- 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.

Description, as the server wrote it:

```untrusted-server-text
Estimate total and per-kg cost from buyer-provided inputs. All amounts must be in one currency. Duty is a total monetary amount, not a percentage. No live freight, duty or supplier quotes are fetched.
```

## Only reads (5)

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

### `calculate_active_cost`

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

Description, as the server wrote it:

```untrusted-server-text
Compare assay-based ingredient costs. Price is per kg; assay is percent (0 < assay <= 100); targetActiveMg is desired active mass per serving. This is formulation arithmetic, not dosage advice.
```

### `get_evidence_coverage`

- The name "get_evidence_coverage" says "get": a word for reading.
- Tag untrusted-input: The description's first sentence says "read" and "review": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Read current coverage counts for the core ingredients, including confirmed offerings and source reviews. These are directory counts, not market-wide statistics.
```

### `get_ingredient`

- The name "get_ingredient" says "get": a word for reading.
- Tag untrusted-input: The description's first sentence says "get" and "review": it reads comments, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Get a botanical ingredient's grades, species, buying considerations and published source reviews. Use the slug from search_ingredients. Includes actual offering counts; does not imply availability.
```

### `search_ingredients`

- The name "search_ingredients" says "search": a word for reading.
- Tag private-data: The description's first sentence says "search" and "note": it reads notes.

Description, as the server wrote it:

```untrusted-server-text
Search CleanIngredients ingredient names, summaries and species notes. Includes core and later-stage research; returns status, source links and review dates. Empty query lists ingredients.
```

### `search_supplier_research`

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

Description, as the server wrote it:

```untrusted-server-text
Search company-published botanical supplier research. Every result is an unconfirmed research lead with a source URL and outstanding evidence checks. No stock, price, sample or quote availability is implied.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__cleaningredients__search_ingredients",
      "mcp__cleaningredients__get_ingredient",
      "mcp__cleaningredients__search_supplier_research",
      "mcp__cleaningredients__get_evidence_coverage",
      "mcp__cleaningredients__calculate_active_cost"
    ],
    "ask": [
      "mcp__cleaningredients__calculate_landed_cost",
      "mcp__cleaningredients__build_sourcing_brief"
    ],
    "deny": []
  }
}
```

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

- `mcp__cleaningredients__search_ingredients`: private-data
- `mcp__cleaningredients__get_ingredient`: untrusted-input
- `mcp__cleaningredients__get_evidence_coverage`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-16T14:19:43.191Z, unchanged since 2026-11-16T14:19:43.191Z. 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 | `2` |
| 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://cleaningredients.co/api/mcp: tools/list returned 7 tools to an anonymous client, including calculate_landed_cost (write), build_sourcing_brief (write)
```
