# ProofTell (npm · @prooftell/mcp)

Phone, email and IP checks and an identity's 0-100 risk score, with one ProofTell API key.

- Trust score: 79/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `@prooftell/mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp.md), [page](https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp)

## Channel facts

- Registry: `npm`
- Package: `@prooftell/mcp`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to prooftell/integrations).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 902 tokens (~180/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the ProofTell MCP server?

ProofTell runs locally as an npm package, launched with npx -y @prooftell/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-prooftell-mcp -- npx -y @prooftell/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-prooftell-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@prooftell/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-prooftell-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@prooftell/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-prooftell-mcp -- npx -y @prooftell/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-prooftell-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@prooftell/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-prooftell-mcp --command npx --arg -y --arg @prooftell/mcp
```

### Hermes

```yaml
mcp_servers:
  com-prooftell-mcp:
    command: "npx"
    args: ["-y", "@prooftell/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-prooftell-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@prooftell/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-prooftell-mcp -t stdio -c npx -a -y @prooftell/mcp
```

### Other

```json
{
  "mcpServers": {
    "com-prooftell-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@prooftell/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-12 (score 79, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

### 2026-11-11 (score 53)

First indexed and scored.

## MCP tools (5)

### `look_up_phone_number` (~209 tokens)

Look up a phone number

Checks a phone number: valid or not, its formats and country, then by level its line type, the carrier it is on today, whether it is live on the network, or a fraud score. The levels are a ladder, each including the ones before it and priced on its own: basic, line_type (the default), current_carrier, line_status, fraud_score; what is not offered for the number comes back as unavailable, at no cost. Charged per check from your balance; the sandbox (a pt_test_ key) is free.

Input parameters:

- `country` (string): The two-letter country code (ISO 3166-1 alpha-2, e.g. GB) of a number given in national format.
- `level` (string): How far to look; line_type when omitted.
- `phone` (string, required): The phone number, in international format (E.164, e.g. +447700900123), or in national format with the country.

### `verify_email_address` (~140 tokens)

Verify an email address

Checks whether an email address accepts mail: a verdict (deliverable, undeliverable, risky, unknown) with its reason, the flags (disposable, role address, catch-all…), the safe action for a sign-up form, and a likely correction of a misspelt domain. Charged per check from your balance; the sandbox (a pt_test_ key) is free.

Input parameters:

- `email` (string, required): The email address, e.g. jane@example.com.
- `timeout` (integer): Milliseconds allowed for the mail server, 1000 to 45000 (the default); past it the address comes back unknown, free.

### `look_up_ip_address` (~94 tokens)

Look up an IP address

Finds where an IP address is and what network it is on (country, city, ASN and organisation), and whether it is Tor, a VPN or a datacenter. Charged per check from your balance; the sandbox (a pt_test_ key) is free.

Input parameters:

- `ip` (string, required): The IPv4 or IPv6 address of the end user, e.g. 203.0.113.1.

### `assess_identity_risk` (~238 tokens)

Assess the risk of an identity

Scores an identity from 0 (no risk found) to 100 with a verdict (allow, review or deny) and the reasons that added to the score, from any mix of phone number, email address and IP address, each checked in parallel; each signal's own result is under signals. Give at least one of the three. Charged per signal from your balance; the sandbox (a pt_test_ key) is free.

Input parameters:

- `country` (string): The two-letter country code (ISO 3166-1 alpha-2, e.g. GB) of a number given in national format.
- `email` (string): The email address, e.g. jane@example.com.
- `ip` (string): The IPv4 or IPv6 address of the end user, e.g. 203.0.113.1.
- `phone` (string): The phone number, in international format (E.164, e.g. +447700900123), or in national format with the country.
- `reference` (string): Your own id for this check (a sign-up, an order), echoed back.

### `get_balance` (~63 tokens)

Get the account's balance

The account's balance in US dollars (paid and promotional money, what is held for running files) and what this month's checks cost so far, by signal. Free. Useful before a batch of checks, or to tell a live key (pt_live_) from the sandbox.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp#diagnostics

## Score history

- 2026-11-21: 79
- 2026-11-20: 79
- 2026-11-19: 79
- 2026-11-18: 79
- 2026-11-17: 79
- 2026-11-16: 79
- 2026-11-15: 79
- 2026-11-14: 79
- 2026-11-13: 79
- 2026-11-12: 79
- 2026-11-11: 53

## Common questions

### What is the ProofTell MCP server?

ProofTell is an MCP server listed in the public MCP registry as com.prooftell/mcp. Phone, email and IP checks and an identity's 0-100 risk score, with one ProofTell API key. This page covers its npm package (@prooftell/mcp).

### Is the ProofTell MCP server safe to use?

ProofTell scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ProofTell MCP server expose?

ProofTell exposes 5 tools: look_up_phone_number, verify_email_address, look_up_ip_address, assess_identity_risk, get_balance. Their descriptions and schemas cost roughly 744 tokens of context every time the server is loaded.

### Is the ProofTell MCP server still maintained?

ProofTell is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ProofTell MCP server under?

ProofTell declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the ProofTell MCP server?

VerifyMCP ran 15 checks on ProofTell, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about ProofTell: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@prooftell/mcp
- Socket report: https://socket.dev/npm/package/@prooftell/mcp
- Repository: https://github.com/prooftell/integrations
- Website: https://prooftell.com/integrations?utm_source=mcp&utm_medium=integration
- Changelog RSS feed: https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-prooftell-mcp/prooftell-mcp
