Call this server's tools from your browser. Nothing to install.
Bearer mt_live_... API key from https://api.malwaretracker.com/portal
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.
Check current MalwareTracker API plan, monthly scan usage, and remaining quota.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcp https://api.malwaretracker.com/mcp
Headers
Authorization (optional, not in the config above): Bearer mt_live_... API key from https://api.malwaretracker.com/portalCheck current MalwareTracker API plan, monthly scan usage, and remaining quota.
No arguments.
{
"type": "object",
"properties": {}
}List or filter MalwareTracker's QuickSand YARA signature catalog, covered CVEs, MITRE ATT&CK techniques, and AI/RAG prompt-injection detection rules. Requires no API key.
| Argument | Type | Description |
|---|---|---|
| cve | string | Optional CVE filter (e.g. 'CVE-2023-38831' or 'CVE-2024-21413'). |
| search | string | Optional keyword to match rule names or descriptions. |
| category | string | Optional rule category filter (e.g. 'ai_safety', 'exploit', 'pdf', 'exe'). |
{
"type": "object",
"properties": {
"cve": {
"type": "string",
"description": "Optional CVE filter (e.g. 'CVE-2023-38831' or 'CVE-2024-21413')."
},
"search": {
"type": "string",
"description": "Optional keyword to match rule names or descriptions."
},
"category": {
"type": "string",
"description": "Optional rule category filter (e.g. 'ai_safety', 'exploit', 'pdf', 'exe')."
}
}
}Look up a previously analyzed document malware & stream report by MD5, SHA1, SHA256, or SHA512 hash. Does not consume monthly scan quota.
| Argument | Type | Description |
|---|---|---|
| hash* | string | Hexadecimal MD5, SHA1, SHA256, or SHA512 file hash. |
{
"type": "object",
"required": [
"hash"
],
"properties": {
"hash": {
"type": "string",
"description": "Hexadecimal MD5, SHA1, SHA256, or SHA512 file hash."
}
}
}Scan a PDF, Office document (DOC/DOCX/XLS/XLSX/PPT/PPTX/RTF/OneNote), email, archive, or extracted text in <100ms for embedded malware exploits, macros, CVEs, and hidden AI/RAG prompt-injection payloads (3 Tr invisible PDF text, zero-point fonts, <w:vanish/> OOXML tags, spoofed <tool_call> tags, and markdown exfiltration beacons) with zero file retention.
| Argument | Type | Description |
|---|---|---|
| filename | string | Original filename (e.g. 'invoice.pdf' or 'resume.docx'). |
| password | string | Optional password for decrypting protected Office documents. |
| text_content | string | Raw UTF-8 text, Markdown, or HTML to inspect if binary bytes are unavailable. |
| content_base64 | string | Base64-encoded bytes of the document to inspect. |
{
"type": "object",
"properties": {
"filename": {
"type": "string",
"default": "document.pdf",
"description": "Original filename (e.g. 'invoice.pdf' or 'resume.docx')."
},
"password": {
"type": "string",
"description": "Optional password for decrypting protected Office documents."
},
"text_content": {
"type": "string",
"description": "Raw UTF-8 text, Markdown, or HTML to inspect if binary bytes are unavailable."
},
"content_base64": {
"type": "string",
"description": "Base64-encoded bytes of the document to inspect."
}
}
}Fast Tier-0 SOAR phishing & attachment triage. Evaluates a document in milliseconds and returns verdict ('clean' | 'suspicious' | 'malicious'), recommended_action ('allow' | 'detonate_in_sandbox' | 'quarantine_and_detonate'), escalate_to_sandbox, matched CVEs, MITRE ATT&CK techniques, and AI prompt-injection findings.
| Argument | Type | Description |
|---|---|---|
| filename | string | Attachment filename (e.g. 'reported_phish.doc'). |
| text_content | string | Raw UTF-8 text/HTML body to triage if binary bytes are unavailable. |
| content_base64 | string | Base64-encoded bytes of the attachment to triage. |
{
"type": "object",
"properties": {
"filename": {
"type": "string",
"default": "attachment.doc",
"description": "Attachment filename (e.g. 'reported_phish.doc')."
},
"text_content": {
"type": "string",
"description": "Raw UTF-8 text/HTML body to triage if binary bytes are unavailable."
},
"content_base64": {
"type": "string",
"description": "Base64-encoded bytes of the attachment to triage."
}
}
}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 12, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.