Skip to content
ScamCheck logo

ScamCheck MCP server

Which MCP servers are ScamCheck's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-10

← Back to ScamCheck

Whose server it is
  • Addresshttps://scamcheck.tech/api/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on scamcheck.tech when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools1
  • Server calls itselfscamcheck
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 107 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • For "check suspicious text messages and links for scams", the likely first call is scan_message.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-27
  • INITE MCP score100 of 100answers 100 · definitions 100 · context 100 · connects 100
  • Answered100% of days7 of 7 daily checks
  • Median first answer132 ms
  • Space in an agent's context≈ 170 tokensthe definitions of all its tools (1), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results1 of 1 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · check suspicious text messages and links for scams
  • not sure · review screenshots for common scam warning signs
  • not sure · get a plain-language reason before replying to a suspicious message

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers1 tools · read 2026-10-27
  • scan_message

    Scan a suspicious message, URL, or text for scam indicators using ScamCheck AI. Returns a verdict (Likely Scam / Suspicious / Likely Safe), risk score 0-100, category, confidence percentage, reasons flagged, and recommended actions. Use…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "scamcheck": {
      "type": "http",
      "url": "https://scamcheck.tech/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http scamcheck https://scamcheck.tech/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://scamcheck.tech/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.