VirusTotal MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_BASE_URL | No | Base URL for the VirusTotal API | https://www.virustotal.com/api/v3 |
| REQUEST_TIMEOUT | No | Timeout for API requests in seconds | 30.0 |
| VIRUSTOTAL_API_KEY | Yes | Your VirusTotal API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct VirusTotal resource and action: file scan/report, URL scan/report, domain report, IP report, comment posting, and search. The paired scan/get tools are clearly differentiated by verb, so an agent should not confuse them.
All tools use a consistent virustotal_ prefix with snake_case and action-first naming (scan_file, get_file_report, post_comment). The lone 'search' is slightly more general but still follows the prefix and casing convention.
Eight tools is well-scoped for a VirusTotal MCP server. It covers the main object types and operations without bloating the surface with rarely used endpoints.
Core workflows are covered: scanning files/URLs and retrieving file/URL/domain/IP reports, plus search and commenting. Minor gaps remain around comment retrieval/management and possibly advanced analysis features, but no critical dead end for typical threat-intel queries.