# `io.usefulapi/emailable` 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.usefulapi/emailable
- JSON: https://radar.anlyon.com/api/v1/servers/io.usefulapi/emailable
- Version: 1.27.4 (active)
- Publisher: io.usefulapi (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/m190/usefulapi-mcp
- Metadata from the official MCP Registry, synced 2026-11-18T11:18:32.850Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Emailable MCP by usefulapi
Verify email addresses with Emailable one by one or in batches, and read credits and batch results.
```

Scanned 2026-10-25T23:19:52.371Z over streamable-http.

**4 tools: 2 can delete or cancel things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 2 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 0 | ask |
| Only reads | read | 2 | 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__emailable__emailable_get_account` `mcp__emailable__emailable_get_batch` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__emailable__emailable_create_batch` `mcp__emailable__emailable_get_account` `mcp__emailable__emailable_get_batch` `mcp__emailable__emailable_verify_email` |
| 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.


## Deletes or cancels (2)

Removes, cancels or revokes something. Claude Code: deny.

### `emailable_create_batch`

- The name "emailable_create_batch" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
- 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
SPENDS CREDITS: starts a bulk verification of up to 5000 email addresses. Emailable takes 1 credit per email when the batch is created, and if the account has too few credits it may charge the account's saved card to buy more. A test_ API key spends nothing. The batch cannot be cancelled here, and the call is never retried: if it fails or times out, check emailable_get_account before trying again, because a retry can charge twice. Returns the batch id; poll it with emailable_get_batch. Emailable's terms allow verification of opt-in subscribers' addresses. POST /v1/batch.
```

### `emailable_verify_email`

- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
- 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
SPENDS CREDITS: verifies one email address and uses 1 Emailable credit (a test_ API key spends none). Returns state (deliverable, undeliverable, risky, unknown), reason, score (0-100), and flags: disposable, free, role, accept_all, no_reply, mailbox_full, plus did_you_mean (a typo fix), the detected user/domain/tag, mx_record and smtp_provider. A credit is returned for an unknown result. The call is never retried automatically. If the reply is {status: "try_again"}, the check took longer than the timeout: call again with the same email; repeats within 5 minutes are not charged. Emailable's terms allow verification of opt-in subscribers' addresses. GET /v1/verify.
```

## Only reads (2)

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

### `emailable_get_account`

- The name "emailable_get_account" says "get": a word for reading.
- Tag private-data: The description's first sentence says "email": it reads mail.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "email": it reads inbound email, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
The Emailable account behind this API key: the owner's email and available_credits. Check it before a large batch. GET /v1/account.
```

### `emailable_get_batch`

- The name "emailable_get_batch" says "get": a word for reading.
- Tag private-data: The description's first sentence says "status" and "message": it reads messages.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "status" and "message": it reads messages, which other people can write.

Description, as the server wrote it:

```untrusted-server-text
Status and results of a batch made with emailable_create_batch: message, progress (processed/total), reason_counts and total_counts (deliverable, undeliverable, risky, unknown). Batches of up to 1,000 emails also return the results inline in `emails` (30 days). They come in pages: up to `limit` results, fewer if the reply would get too long; ask for the next page with emails_page.next_offset. A bigger batch returns download_file, a temporary link (5 days) to a ZIP of a CSV: share it only with the account owner. Free to call. GET /v1/batch.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__emailable__emailable_get_account",
      "mcp__emailable__emailable_get_batch"
    ],
    "ask": [],
    "deny": [
      "mcp__emailable__emailable_verify_email",
      "mcp__emailable__emailable_create_batch"
    ]
  }
}
```

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

- `mcp__emailable__emailable_get_account`: private-data, untrusted-input
- `mcp__emailable__emailable_verify_email`: untrusted-input
- `mcp__emailable__emailable_create_batch`: untrusted-input
- `mcp__emailable__emailable_get_batch`: private-data, untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:35:31.694Z, unchanged since 2026-10-29T22:30:45.294Z. 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 | `no` |
| HTTP status of an anonymous initialize | `none` |
| tools/list served without credentials | `no` |
| Tools that change things, listed without credentials | `0` |
| Protocol version | `none` |
| 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` |

Probe stopped: `The server redirected a POST to a different request.`

Posture changes:

- 2026-10-29T22:30:45.294Z: Reachable `yes` -> `no`; HTTP status of an anonymous initialize `200` -> `none`; tools/list served without credentials `yes` -> `no`; Tools that change things, listed without credentials `2` -> `0`; Protocol version `2025-06-18` -> `none`; RFC 9728 protected resource metadata `https://emailable.usefulapi.io/.well-known/oauth-protected-resource/mcp` -> `none`; Authorization servers `https://emailable.usefulapi.io` -> `none`; Dynamic client registration `yes` -> `not observed`; Client ID metadata documents `no` -> `not observed`
