Free anti-scam intelligence: search cases, check risk, list scam types, reporting channels.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Analyze a suspicious message, email or text for known scam red flags using deterministic rules. Returns a risk level (LOW/MEDIUM/HIGH/CRITICAL) and the matched warning signs.
The message or text to evaluate
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http scamnav https://scamnav.com/mcp
Analyze a suspicious message, email or text for known scam red flags using deterministic rules. Returns a risk level (LOW/MEDIUM/HIGH/CRITICAL) and the matched warning signs.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| text* | string | The message or text to evaluate |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"text"
],
"properties": {
"lang": {
"enum": [
"en",
"zh",
"zhtw",
"es",
"fr",
"de",
"pt",
"ru",
"ar",
"ja",
"ko",
"hi",
"vi",
"id",
"th",
"he"
],
"type": "string"
},
"text": {
"type": "string",
"maxLength": 4000,
"minLength": 1,
"description": "The message or text to evaluate"
}
},
"additionalProperties": false
}List official scam/cybercrime reporting channels. Optionally filter by region code. Only official authorities are included; no recovery or fund-recovery services.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| region | string | Optional region code, e.g. US, HK, IN |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"lang": {
"enum": [
"en",
"zh",
"zhtw",
"es",
"fr",
"de",
"pt",
"ru",
"ar",
"ja",
"ko",
"hi",
"vi",
"id",
"th",
"he"
],
"type": "string"
},
"region": {
"type": "string",
"description": "Optional region code, e.g. US, HK, IN"
}
},
"additionalProperties": false
}Retrieve one scam case by slug, including sections and FAQs, in the requested language. Use search_scams first to find a slug.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| slug* | string | Case slug, e.g. ftc-impersonation |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"lang": {
"enum": [
"en",
"zh",
"zhtw",
"es",
"fr",
"de",
"pt",
"ru",
"ar",
"ja",
"ko",
"hi",
"vi",
"id",
"th",
"he"
],
"type": "string"
},
"slug": {
"type": "string",
"minLength": 1,
"description": "Case slug, e.g. ftc-impersonation"
}
},
"additionalProperties": false
}List all distinct scam types currently covered in the knowledge base.
No arguments.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Search the ScamNav anti-scam knowledge base by keyword across titles, summaries, tags and scam types. Returns matching cases in the requested language.
| Argument | Type | Description |
|---|---|---|
| lang | string | |
| query* | string | Keyword, brand, domain or tactic to search |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"lang": {
"enum": [
"en",
"zh",
"zhtw",
"es",
"fr",
"de",
"pt",
"ru",
"ar",
"ja",
"ko",
"hi",
"vi",
"id",
"th",
"he"
],
"type": "string"
},
"query": {
"type": "string",
"minLength": 1,
"description": "Keyword, brand, domain or tactic to search"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.