About scamcheck-mcp-server
scamcheck-mcp-server lets AI assistants scan messages, URLs, and text for scam indicators. It offers an anonymous tier without an API key, with optional keys for higher limits.
Key features
- 01Scan messages, URLs, and text
- 02Classify risk and scam category
- 03Explain why content was flagged
- 04Anonymous use without an API key
Use cases
- 01Check a suspicious message before responding
- 02Review a URL for phishing indicators
MCP support
It exposes the `scan_message` tool to MCP clients, accepting text, URLs, or screenshot content and returning an analysis.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://scamcheck.tech/api/mcpclaude mcp add --transport http smijo-geek-scamcheck https://scamcheck.tech/api/mcp{"mcpServers":{"smijo-geek-scamcheck":{"type":"http","url":"https://scamcheck.tech/api/mcp"}}}Open in Cursor{"servers":{"smijo-geek-scamcheck":{"type":"http","url":"https://scamcheck.tech/api/mcp"}}}Open in VS Code{"mcpServers":{"smijo-geek-scamcheck":{"type":"http","url":"https://scamcheck.tech/api/mcp"}}}{"mcpServers":{"smijo-geek-scamcheck":{"serverUrl":"https://scamcheck.tech/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
1| Parameter | Type | Required | Description |
|---|---|---|---|
| input | string | Yes | The message, URL, or text to scan. Minimum 8 characters. |
| source | enum | No | Content type: text (default), url, or screenshot.text | url | screenshot |
Details
From the project READMEScamCheck MCP Server
Scan suspicious messages, URLs, and text for scams inside any AI assistant that supports MCP (Claude Desktop, Claude Code, Cursor, and more). No signup or API key needed — works out of the box on the free anonymous tier.
Quick start (no API key)
Add to your Claude Desktop / Cursor config:
{
"mcpServers": {
"scamcheck": {
"command": "npx",
"args": ["scamcheck-mcp-server"]
}
}
}
That's it. Ask your assistant "is this message a scam?" and paste the message.
Higher limits (optional API key)
The anonymous tier is rate-limited per IP. For higher limits, grab a free key at scamcheck.tech/dashboard/developer and add it:
{
"mcpServers": {
"scamcheck": {
"command": "npx",
"args": ["scamcheck-mcp-server"],
"env": {
"SCAMCHECK_API_KEY": "sk-live-your-key-here"
}
}
}
}
Tool: scan_message
| Parameter | Type | Required | Description |
|---|---|---|---|
input | string | ✓ | The message, URL, or text to scan |
source | text | url | screenshot | — | Content type (default: text) |
Example response
🔴 Likely Scam — Risk Score: 89/100
Category: phishing · Confidence: 92%
Summary: This message impersonates a bank to steal credentials.
Why this was flagged:
• Creates false urgency with account suspension threat
• Uses a URL that does not match the official bank domain
• Requests sensitive personal information via link
What to do:
✓ Do not click any links in this message
✓ Contact your bank directly using the number on your card
✓ Report to your bank's fraud department
Full report: https://scamcheck.tech/result/abc123
Rate limits
- Anonymous (no key): IP rate-limited
- Free API key: 100 scans/month
- Pro/Business: Unlimited
Install in Claude Desktop (one click)
Download scamcheck.mcpb and double-click it, or drag it into Claude Desktop → Settings → Extensions. The API key field is optional; leave it blank to use the free tier.
Privacy Policy
Full policy: scamcheck.tech/privacy
- What is collected: only the text or URL you ask the
scan_messagetool to check, plus the optional API key you configure. The extension reads nothing else from your computer or your conversations. - How it is used: the content is sent over HTTPS to the ScamCheck API (
scamcheck.tech) and analysed to produce the verdict. Anonymous requests are rate-limited by IP address. - Storage and retention: scans may be stored to generate a shareable result link and to improve detection. Retention is described in the full policy linked above.
- Third parties: ScamCheck uses an AI model provider to analyse scans. Your data is not sold or used for advertising.
- Contact: privacy questions or deletion requests go to support via scamcheck.tech or the GitHub issues.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.