# `com.verirouteintel/lookup` 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/com.verirouteintel/lookup
- JSON: https://radar.anlyon.com/api/v1/servers/com.verirouteintel/lookup
- Version: 1.2.3 (active)
- Publisher: com.verirouteintel (domain proven to the MCP Registry)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/verirouteintel/veriroute-intel-mcp
- Metadata from the official MCP Registry, synced 2026-10-21T18:10:49.278Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Is this number safe to call or text right now? Live carrier, CNAM, spam and SMS checks for agents.
```

Scanned 2026-11-11T05:17:51.333Z over streamable-http.

**10 tools: 8 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 8 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

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

| 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. | `mcp__lookup__vri_bulk_lookup` `mcp__lookup__vri_bulk_status` `mcp__lookup__vri_number_lookup` `mcp__lookup__vri_sms_deliverability` `mcp__lookup__vri_spam_check` `mcp__lookup__vri_submit_job` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__lookup__vri_bulk_lookup` `mcp__lookup__vri_number_lookup` `mcp__lookup__vri_quote` `mcp__lookup__vri_sms_deliverability` `mcp__lookup__vri_spam_check` `mcp__lookup__vri_submit_job` |

## Findings

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

```untrusted-server-text
The server marks "vri_number_lookup" as not read-only (readOnlyHint: false), and its words say it reads.

annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "vri_number_lookup" says "lookup": a word for reading.
```

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

```untrusted-server-text
The server marks "vri_bulk_lookup" as not read-only (readOnlyHint: false), and its words say it reads.

annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "vri_bulk_lookup" says "lookup": a word for reading.
```


## Changes things (8)

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

### `vri_account_info`

- 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
Free: available balance, connection limits and allowed products. When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically.
```

### `vri_bulk_lookup`

- The name "vri_bulk_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a destination (input.phone_numbers): what the tool writes goes there.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Live lookup for up to 100 North American phone numbers in one call (carrier, line type, routing; optional cnam/spam/messaging). Each number is a fresh paid read — spend scope required. When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
```

### `vri_job_results`

- 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
Free, owner-scoped stored results. Follow next_cursor until null; never re-submit a completed job. When returned, show job_ui_url for browser progress and use results_tool with results_tool_arguments to read stored results. Links require authentication and do not guarantee results are ready.
```

### `vri_number_lookup`

- The name "vri_number_lookup" says "lookup": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a destination (input.phone_number): what the tool writes goes there.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Live intelligence for ONE North American phone number: current carrier of record, line type, LRN routing data, porting activation date, and optionally caller-ID name (cnam), spam reputation, and messaging provider. Always a fresh read of live numbering infrastructure — never cached carrier data. When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
```

### `vri_quote`

- 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.
- Tag outbound: The input takes a destination (input.phone_numbers): what the tool writes goes there.

Description, as the server wrote it:

```untrusted-server-text
Free estimate using account pricing and deduplicated valid numbers; no lookup. When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically.
```

### `vri_sms_deliverability`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a destination (input.phone_number): what the tool writes goes there.

Description, as the server wrote it:

```untrusted-server-text
Line-type-based SMS capability and reputation signals for a North American number. Not an actual delivery test or guarantee. Unknown reputation never clears a number to message. Returns sms_capable (live line-type read), VoIP flag, spam reputation, the recipient's approximate local time with an 8am-9pm calling-window flag, and plain-language reasons. Deliverability and reputation signals only — not a legal compliance determination (no DNC/reassigned-number/litigator data). Performs its own LRN and spam lookup; avoid calling after number_lookup for the same data. When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
```

### `vri_spam_check`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a destination (input.phone_number): what the tool writes goes there.

Description, as the server wrote it:

```untrusted-server-text
Spam/scam/robocall reputation for one North American phone number, with an explainable `risk` block: the verdict, a confidence band, and the individual reasons behind it (complaint volume and recency, complaint category, community reports, line type, recent porting). When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
```

### `vri_submit_job`

- The name "vri_submit_job" says "submit": a word for a change.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a destination (input.phone_numbers): what the tool writes goes there.

Description, as the server wrote it:

```untrusted-server-text
Submit an ASYNC bulk lookup job for up to 10000 North American phone numbers. Balance is reserved up front and the job runs in the background; check progress with vri_bulk_status. Requires a customer API key (jobs bill the account that owns the key). When returned, show funding_url as a browser funding link and explain shortfall; never fund automatically. When returned, show job_ui_url for browser progress and use results_tool with results_tool_arguments to read stored results. Links require authentication and do not guarantee results are ready. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.
```

## Only reads (2)

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

### `vri_bulk_status`

- The name "vri_bulk_status" says "status": a word for reading.
- 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
Status and progress of a VRI bulk lookup job by job id. When returned, show job_ui_url for browser progress and use results_tool with results_tool_arguments to read stored results. Links require authentication and do not guarantee results are ready.
```

### `vri_operation_status`

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

Description, as the server wrote it:

```untrusted-server-text
Free: check an operation after an interrupted call; pending work must not be resubmitted with a new ID. When returned, show job_ui_url for browser progress and use results_tool with results_tool_arguments to read stored results. Links require authentication and do not guarantee results are ready.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__lookup__vri_bulk_status",
      "mcp__lookup__vri_operation_status"
    ],
    "ask": [
      "mcp__lookup__vri_number_lookup",
      "mcp__lookup__vri_spam_check",
      "mcp__lookup__vri_bulk_lookup",
      "mcp__lookup__vri_sms_deliverability",
      "mcp__lookup__vri_submit_job",
      "mcp__lookup__vri_account_info",
      "mcp__lookup__vri_quote",
      "mcp__lookup__vri_job_results"
    ],
    "deny": []
  }
}
```

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

- `mcp__lookup__vri_number_lookup`: untrusted-input, outbound
- `mcp__lookup__vri_spam_check`: untrusted-input, outbound
- `mcp__lookup__vri_bulk_status`: untrusted-input
- `mcp__lookup__vri_bulk_lookup`: untrusted-input, outbound
- `mcp__lookup__vri_sms_deliverability`: untrusted-input, outbound
- `mcp__lookup__vri_submit_job`: untrusted-input, outbound
- `mcp__lookup__vri_quote`: outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:49:53.205Z, unchanged since 2026-10-22T14:43:42.792Z. 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 | `8` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `https://verirouteintel.com/.well-known/oauth-protected-resource/api/mcp` |
| Authorization servers | `https://verirouteintel.com` |
| 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 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

https://verirouteintel.com/api/mcp: tools/list returned 10 tools to an anonymous client, including vri_number_lookup (write), vri_spam_check (write), vri_bulk_lookup (write), vri_sms_deliverability (write), vri_submit_job (write) and 3 more
```
