# scamgate (pypi · scamgate)

Offline scam check for agents: verify links and payments before acting (allow, ask or deny).

- Trust score: 70/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `scamgate`: 70/100 (this document), [markdown](https://verifymcp.io/servers/odaiameera-scamgate/scamgate.md), [page](https://verifymcp.io/servers/odaiameera-scamgate/scamgate)

## Channel facts

- Registry: `pypi`
- Package: `scamgate`
- Version: `0.3.3`
- 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 2026-11-04.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 4 of 37 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to odaiameera/scamgate).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 500 tokens (~166/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

scamgate runs locally as a PyPI package, launched with uvx scamgate. 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 odaiameera-scamgate -- uvx scamgate
```

### Cursor

```json
{
  "mcpServers": {
    "odaiameera-scamgate": {
      "command": "uvx",
      "args": [
        "scamgate"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "odaiameera-scamgate": {
      "command": "uvx",
      "args": [
        "scamgate"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add odaiameera-scamgate -- uvx scamgate
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "odaiameera-scamgate": {
      "type": "local",
      "command": [
        "uvx",
        "scamgate"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add odaiameera-scamgate --command uvx --arg scamgate
```

### Hermes

```yaml
mcp_servers:
  odaiameera-scamgate:
    command: "uvx"
    args: ["scamgate"]
```

### Netclaw

```json
{
  "McpServers": {
    "odaiameera-scamgate": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "scamgate"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add odaiameera-scamgate -t stdio -c uvx -a scamgate
```

### Other

```json
{
  "mcpServers": {
    "odaiameera-scamgate": {
      "command": "uvx",
      "args": [
        "scamgate"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 68, −14)

- [security regression] Malware scan: pass → unverified

### 2026-10-29 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-28 (score 67, −14)

- [security regression] Malware scan: pass → unverified

### 2026-10-26 (score 81)

First indexed and scored.

## MCP tools (3)

### `check_url` (~117 tokens)

Check a link before opening it. Returns a verdict: decision (allow | ask | deny), risk_score 0-100, plain-English reasons, and checked_host, the host the link really opens. If the decision is ask, stop and show the reasons to the human. If deny, do not proceed. Results are advisory, not a guarantee.

Input parameters:

- `intent`: What the agent is trying to do, e.g. "book a hotel in Galway".
- `url` (string, required): The full URL the agent is about to open.

Output parameters:

- `advisory` (string)
- `checked_host`: For links: the host scamgate judged, the one a browser would open. If it isn't where you expected the link to go, treat that as a warning. Empty for payments and unreadable links.
- `decision`
- `reasons` (array)
- `risk_score` (integer)
- `summary` (string)
- `warnings` (array): Notes about the check itself, e.g. a stale feed cache

### `check_payment` (~238 tokens)

Check a payment before making it. Returns a verdict: decision (allow | ask | deny), risk_score 0-100 and plain-English reasons. If the decision is ask, stop and show the reasons to the human. If deny, do not proceed. Results are advisory, not a guarantee.

Input parameters:

- `amount` (number, required): Amount to pay.
- `bank_details_changed`: True if the payee's account details changed recently.
- `budget`: The spending limit the human gave for this task.
- `context_text`: The messages or page text that led to this payment.
- `currency` (string, required): e.g. EUR, GBP, USDT.
- `is_new_payee`: True if this payee has never been paid before. scamgate checks your payee history rather than taking this on trust.
- `method` (string, required): card, bank_transfer, crypto, gift_card or other.
- `payee_account` (string, required): IBAN, wallet address, merchant id, etc.
- `payee_name` (string, required): Who is being paid.
- `vop_result`: Verification of Payee result, if available.

Output parameters:

- `advisory` (string)
- `checked_host`: For links: the host scamgate judged, the one a browser would open. If it isn't where you expected the link to go, treat that as a warning. Empty for payments and unreadable links.
- `decision`
- `reasons` (array)
- `risk_score` (integer)
- `summary` (string)
- `warnings` (array): Notes about the check itself, e.g. a stale feed cache

### `update_feeds` (~77 tokens)

Refresh scamgate's phishing lists now. Use it when a scamgate verdict or status says the lists are missing or stale. Takes no arguments: it always downloads the default lists from their fixed sources, and does nothing if they were refreshed in the last hour. With automatic refresh on, the lists also refresh by themselves every 6 hours.

Output parameters:

- `failed` (object): Lists that couldn't be downloaded; their old copy is kept.
- `not_configured` (object): Optional lists that need a key first.
- `skipped` (string): "fresh" (refreshed in the last hour), "busy" (another refresh is running) or empty.
- `summary` (string): One line per list, for the human.
- `updated` (array): Lists downloaded now.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/odaiameera-scamgate/scamgate#diagnostics

## Score history

- 2026-11-04: 70
- 2026-11-03: 70
- 2026-11-02: 69
- 2026-11-01: 69
- 2026-10-31: 68
- 2026-10-30: 68
- 2026-10-29: 82
- 2026-10-28: 67
- 2026-10-27: 81
- 2026-10-26: 81

## Common questions

### What is the scamgate MCP server?

scamgate is an MCP server listed in the public MCP registry as io.github.odaiameera/scamgate. Offline scam check for agents: verify links and payments before acting (allow, ask or deny). This page covers its PyPI package (scamgate).

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

scamgate scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. 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 scamgate MCP server expose?

scamgate exposes 3 tools: check_url, check_payment, update_feeds. Their descriptions and schemas cost roughly 432 tokens of context every time the server is loaded.

### Is the scamgate MCP server still maintained?

scamgate is still listed as active in the MCP registry. We last reached this channel on 4 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 scamgate MCP server under?

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

## Links

- PyPI project: https://pypi.org/project/scamgate/
- Socket report: https://socket.dev/pypi/package/scamgate
- Repository: https://github.com/odaiameera/scamgate
- Website: https://odaiameera.github.io/scamgate/
- Changelog RSS feed: https://verifymcp.io/servers/odaiameera-scamgate/scamgate.xml
- Changelog JSON feed: https://verifymcp.io/servers/odaiameera-scamgate/scamgate.json
- HTML version of this page: https://verifymcp.io/servers/odaiameera-scamgate/scamgate