Provides tools for interacting with VirusTotal API, enabling security analysis of URLs, files, IP addresses, and domains with automatic relationship data fetching.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@VirusTotal MCP Server analyze file hash e99a18c428cb38d5f260853678922e03"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for querying the VirusTotal API. This server provides comprehensive security analysis tools with automatic relationship data fetching. It integrates seamlessly with MCP-compatible applications like Claude Desktop.
To install VirusTotal Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @burtthecoder/mcp-virustotal --client claudeInstall the server globally via npm:
npm install -g @burtthecoder/mcp-virustotalAdd to your Claude Desktop configuration file:
{
"mcpServers": {
"virustotal": {
"command": "mcp-virustotal",
"env": {
"VIRUSTOTAL_API_KEY": "your-virustotal-api-key"
}
}
}
}Configuration file location:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop
Related MCP server: FastMCP ThreatIntel
If you prefer to run from source or need to modify the code:
Clone and build:
git clone <repository_url>
cd mcp-virustotal
npm install
npm run buildAdd to your Claude Desktop configuration:
{
"mcpServers": {
"virustotal": {
"command": "node",
"args": ["--experimental-modules", "/absolute/path/to/mcp-virustotal/build/index.js"],
"env": {
"VIRUSTOTAL_API_KEY": "your-virustotal-api-key"
}
}
}
}Comprehensive Analysis Reports: Each analysis tool automatically fetches relevant relationship data along with the basic report, providing a complete security overview in a single request
URL Analysis: Security reports with automatic fetching of contacted domains, downloaded files, and threat actors
File Analysis: Detailed analysis of file hashes including behaviors, dropped files, and network connections
IP Analysis: Security reports with historical data, resolutions, and related threats
Domain Analysis: DNS information, WHOIS data, SSL certificates, and subdomains
Detailed Relationship Analysis: Dedicated tools for querying specific types of relationships with pagination support
Rich Formatting: Clear categorization and presentation of analysis results and relationship data
Name: get_url_report
Description: Get a comprehensive URL analysis report including security scan results and key relationships (communicating files, contacted domains/IPs, downloaded files, redirects, threat actors)
Parameters:
url (required): The URL to analyze
Name: get_file_report
Description: Get a comprehensive file analysis report using its hash (MD5/SHA-1/SHA-256). Includes detection results, file properties, and key relationships (behaviors, dropped files, network connections, embedded content, threat actors)
Parameters:
hash (required): MD5, SHA-1 or SHA-256 hash of the file
Name: get_ip_report
Description: Get a comprehensive IP address analysis report including geolocation, reputation data, and key relationships (communicating files, historical certificates/WHOIS, resolutions)
Parameters:
ip (required): IP address to analyze
Name: get_domain_report
Description: Get a comprehensive domain analysis report including DNS records, WHOIS data, and key relationships (SSL certificates, subdomains, historical data)
Parameters:
domain (required): Domain name to analyze
relationships (optional): Array of specific relationships to include in the report
Name: get_url_relationship
Description: Query a specific relationship type for a URL with pagination support. Choose from 17 relationship types including analyses, communicating files, contacted domains/IPs, downloaded files, graphs, referrers, redirects, and threat actors
Parameters:
url (required): The URL to get relationships for
relationship (required): Type of relationship to query
Available relationships: analyses, comments, communicating_files, contacted_domains, contacted_ips, downloaded_files, graphs, last_serving_ip_address, network_location, referrer_files, referrer_urls, redirecting_urls, redirects_to, related_comments, related_references, related_threat_actors, submissions
limit (optional, default: 10): Maximum number of related objects to retrieve (1-40)
cursor (optional): Continuation cursor for pagination
Name: get_file_relationship
Description: Query a specific relationship type for a file with pagination support. Choose from 41 relationship types including behaviors, network connections, dropped files, embedded content, execution chains, and threat actors
Parameters:
hash (required): MD5, SHA-1 or SHA-256 hash of the file
relationship (required): Type of relationship to query
Available relationships: analyses, behaviours, bundled_files, carbonblack_children, carbonblack_parents, ciphered_bundled_files, ciphered_parents, clues, collections, comments, compressed_parents, contacted_domains, contacted_ips, contacted_urls, dropped_files, email_attachments, email_parents, embedded_domains, embedded_ips, embedded_urls, execution_parents, graphs, itw_domains, itw_ips, itw_urls, memory_pattern_domains, memory_pattern_ips, memory_pattern_urls, overlay_children, overlay_parents, pcap_children, pcap_parents, pe_resource_children, pe_resource_parents, related_references, related_threat_actors, similar_files, submissions, screenshots, urls_for_embedded_js, votes
limit (optional, default: 10): Maximum number of related objects to retrieve (1-40)
cursor (optional): Continuation cursor for pagination
Name: get_ip_relationship
Description: Query a specific relationship type for an IP address with pagination support. Choose from 12 relationship types including communicating files, historical SSL certificates, WHOIS records, resolutions, and threat actors
Parameters:
ip (required): IP address to analyze
relationship (required): Type of relationship to query
Available relationships: comments, communicating_files, downloaded_files, graphs, historical_ssl_certificates, historical_whois, related_comments, related_references, related_threat_actors, referrer_files, resolutions, urls
limit (optional, default: 10): Maximum number of related objects to retrieve (1-40)
cursor (optional): Continuation cursor for pagination
Name: get_domain_relationship
Description: Query a specific relationship type for a domain with pagination support. Choose from 21 relationship types including SSL certificates, subdomains, historical data, and DNS records
Parameters:
domain (required): Domain name to analyze
relationship (required): Type of relationship to query
Available relationships: caa_records, cname_records, comments, communicating_files, downloaded_files, historical_ssl_certificates, historical_whois, immediate_parent, mx_records, ns_records, parent, referrer_files, related_comments, related_references, related_threat_actors, resolutions, soa_records, siblings, subdomains, urls, user_votes
limit (optional, default: 10): Maximum number of related objects to retrieve (1-40)
cursor (optional): Continuation cursor for pagination
Node.js (v18 or later)
A valid VirusTotal API Key
If you see "Wrong API key" errors:
Check the log file at /tmp/mcp-virustotal-server.log (on macOS) for API key status
Verify your API key:
Should be a valid VirusTotal API key (usually 64 characters)
No extra spaces or quotes around the key
Must be from the API Keys section in your VirusTotal account
After any configuration changes:
Save the config file
Restart Claude Desktop
Check logs for new API key status
If you see ES module loading warnings:
For global installation: Use the simple configuration shown in Quick Start
For source installation: Ensure you include --experimental-modules in the args
To run in development mode with hot reloading:
npm run devThe server includes comprehensive error handling for:
Invalid API keys
Rate limiting
Network errors
Invalid input parameters
Invalid hash formats
Invalid IP formats
Invalid URL formats
Invalid relationship types
Pagination errors
v1.0.0: Initial release with core functionality
v1.1.0: Added relationship analysis tools for URLs, files, and IP addresses
v1.2.0: Added improved error handling and logging
v1.3.0: Added pagination support for relationship queries
v1.4.0: Added automatic relationship fetching in report tools and domain analysis support
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Get a comprehensive domain analysis report including DNS records, WHOIS data, and key relationships (SSL certificates, subdomains, historical data). Optionally specify which relationships to include in the report. Returns both the basic analysis and relationship data.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes | Domain name to analyze | |
| relationships | No | Optional array of relationships to include in the report |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears the full burden of behavioral disclosure. It describes report contents and return values, but it fails to explicitly state that the operation is read-only, potential performance implications (e.g., multiple DNS lookups), error handling, or required permissions. The read-only nature is implied by the word 'report' but not declared.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences long with a clear structure, front-loading the primary action and content list. The final sentence about returning both basic analysis and relationship data is mildly redundant with the first sentence, but overall it is concise and free of unnecessary filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Since there is no output schema, the description provides a high-level overview of return content but lacks specifics on response format, error conditions, or pagination. For a report tool, this is adequate for basic selection, but it does not fully cover edge cases or operational details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters are fully described in the schema, giving 100% coverage. The description adds a high-level summary of relationship types (SSL certificates, subdomains, historical data) but does not introduce new syntactic or semantic detail beyond the schema's enum and pattern. The baseline of 3 applies as the schema already handles parameter documentation adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with the verb 'Get' and identifies the specific resource: a comprehensive domain analysis report. It enumerates included data (DNS records, WHOIS, SSL certificates, subdomains, historical data), distinguishing it from sibling tools that focus on URLs, files, or IPs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for domain analysis, but it does not explicitly mention when to use it over sibling tools or provide exclusions. It mentions optional relationships as a customization, but no direct alternative references or specific use cases are given, leaving usage guidance implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query a specific relationship type for a file with pagination support. Choose from 41 relationship types including behaviors, network connections, dropped files, embedded content, execution chains, and threat actors. Useful for detailed investigation of specific relationship types.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes | MD5, SHA-1 or SHA-256 hash of the file | |
| limit | No | ||
| cursor | No | ||
| relationship | Yes | Type of relationship to query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses pagination support and the scope of 41 relationship types, but does not explicitly state that the operation is read-only, nor does it describe result structure, error conditions, or rate limits. This is a modest behavioral transparency for a query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is exactly two sentences, front-loaded with the core purpose, and every sentence adds value. The list of relationship categories is efficient and illustrative, with no redundant or filler text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 4-parameter tool with no annotations and no output schema, the description provides purpose, pagination, and relationship types, but leaves gaps: it does not mention that limit and cursor are optional, does not describe return values or pagination mechanics, and does not differentiate from sibling relationship tools beyond the 'file' scope. It is adequate but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (hash and relationship have descriptions; limit and cursor do not). The description adds meaning by listing relationship categories and mentioning pagination, but it does not explain how to use limit/cursor or the hash format. It partially compensates for the schema gap but not fully.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Query') with a clear resource ('a specific relationship type for a file') and distinguishes from sibling tools by explicitly scoping to files. It also provides concrete examples of relationship categories, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool ('detailed investigation of specific relationship types') and implies it is for file relationships specifically, but it does not explicitly name alternatives or state when not to use it. This is a clear context with no exclusions, meeting the '4' criterion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a comprehensive file analysis report using its hash (MD5/SHA-1/SHA-256). Includes detection results, file properties, and key relationships (behaviors, dropped files, network connections, embedded content, threat actors). Returns both the basic analysis and automatically fetched relationship data.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes | MD5, SHA-1 or SHA-256 hash of the file |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses a non-obvious behavior: automatically fetching relationship data in addition to the basic analysis. It also specifies what content is included. However, it does not mention potential latency, failure modes, or whether any auth/permissions are required, but for a read-only 'get' tool, the disclosure of auto-fetching is valuable and goes beyond a minimal description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with purpose, and every phrase earns its place. It succinctly lists report contents and the auto-fetch behavior without redundancy or fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter and no output schema, the description provides a reasonable overview of the return content ('detection results, file properties, and key relationships') and the fact that it returns both basic analysis and relationship data. It does not specify the exact output format, but that is not required when an output schema is absent. The description is sufficiently complete for a simple get-by-hash tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the only parameter, 'hash', is already described in the schema as 'MD5, SHA-1 or SHA-256 hash of the file'. The description repeats this information ('using its hash (MD5/SHA-1/SHA-256)') without adding new meaning like format details, examples, or validation rules. Baseline 3 applies since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') with a clear resource ('comprehensive file analysis report') and identifies the input (hash). It lists what the report includes (detection results, file properties, relationships), and distinguishes itself from sibling tools like get_url_report or get_file_relationship by noting it returns both basic analysis and automatically fetched relationship data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context: use when you need a comprehensive file report by hash. It does not explicitly name alternatives or exclusions, but the scope is evident from the resource type (file) and the inclusion of relationships, which separates it from get_file_relationship. No explicit when-not-to-use is stated, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query a specific relationship type for an IP address with pagination support. Choose from 12 relationship types including communicating files, historical SSL certificates, WHOIS records, resolutions, and threat actors. Useful for detailed investigation of specific relationship types.
| Name | Required | Description | Default |
|---|---|---|---|
| ip | Yes | IP address to analyze | |
| limit | No | ||
| cursor | No | ||
| relationship | Yes | Type of relationship to query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the transparency burden. It discloses pagination support and lists relationship types, but does not describe the response format, error behavior, or explicitly confirm a read-only nature. The verb 'Query' implies a read operation but lacks explicit safety cues.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two succinct sentences, front-loaded with the core action and resource. It includes useful relationship type examples and a use case without redundancy, making it efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description should provide more context about return values and pagination details. It covers purpose and use case well but omits the response structure and cursor mechanics, making it adequate but not comprehensive for a tool with four parameters and no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers ip and relationship with descriptions, but limit and cursor have no descriptions. The description mentions pagination support, which hints at the purpose of limit and cursor, but does not explain cursor usage or response token mechanics, so it only partially compensates for the schema's missing semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Query' and the resource 'a specific relationship type for an IP address', which distinguishes it from sibling relationship tools for other entities. It also lists example relationship types, making the tool's scope immediately understandable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Useful for detailed investigation of specific relationship types' provides clear context for when to use the tool. However, it does not explicitly mention alternatives or when not to use it, such as referring to get_ip_report for a broader overview.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a comprehensive IP address analysis report including geolocation, reputation data, and key relationships (communicating files, historical certificates/WHOIS, resolutions). Returns both the basic analysis and automatically fetched relationship data.
| Name | Required | Description | Default |
|---|---|---|---|
| ip | Yes | IP address to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that relationship data is 'automatically fetched', which is a behavioral trait beyond a simple read, but it does not mention potential side effects, rate limits, or whether any network calls are made. The description does not explicitly state it is read-only, though the verb 'get' implies it. Some transparency is present, but significant gaps remain.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action and resource, and every phrase adds value. It efficiently lists what the report includes and highlights the dual return of basic and relationship data without fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of an IP report tool with no output schema, the description provides a good inventory of what is returned (geolocation, reputation, relationships) and mentions both basic analysis and auto-fetched relationships. It lacks specifics about the return structure or any limitations, but for a single-parameter tool, this is sufficient to guide an agent. Slight deduction for not mentioning potential response size or filtering options.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the only parameter 'ip', which already includes a clear description ('IP address to analyze'). The tool description adds no additional meaning to the parameter beyond restating it in context. Baseline of 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Get a comprehensive IP address analysis report' with a specific verb and resource. It lists concrete contents (geolocation, reputation, key relationships) and distinguishes itself from sibling tools by emphasizing the comprehensive nature and inclusion of both basic analysis and relationship data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this is the go-to tool for full IP analysis, but it does not explicitly state when to use it versus alternatives like get_ip_relationship. Since the sibling tool exists for relationships, mentioning that this tool includes relationships could be confusing without explicit usage boundaries. No when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query a specific relationship type for a URL with pagination support. Choose from 17 relationship types including analyses, communicating files, contacted domains/IPs, downloaded files, graphs, referrers, redirects, and threat actors. Useful for detailed investigation of specific relationship types.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to get relationships for | |
| limit | No | ||
| cursor | No | ||
| relationship | Yes | Type of relationship to query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses pagination support and specificity of relationship type, which are valuable. However, it omits response structure, error behavior, or authentication requirements. It also doesn't explicitly state it's a read-only operation (though the name implies it), so transparency is partial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences: the first states the core action clearly, the second gives examples of relationship types, and the third adds usage context. The last sentence is slightly redundant but concise overall; no excessive filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is moderately complex with 4 parameters and an enum, but the description omits any mention of return format (since there is no output schema). It covers the main purpose and pagination, but does not explain how to handle multiple pages or what the response contains, leaving completeness incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 50% (url and relationship have descriptions; limit and cursor do not). The description adds 'pagination support' to give meaning to limit/cursor and lists examples of relationship types. It does not fully describe cursor semantics, so it adds some but not complete value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses 'Query a specific relationship type for a URL' with a list of example relationship types. This clearly identifies the resource and operation, and distinguishes from sibling tools like get_url_report (which returns a report) and get_file_relationship/get_ip_relationship (which target different entities).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It states 'Useful for detailed investigation of specific relationship types,' which gives a clear context for when to use it. However, it does not explicitly name alternatives or state when not to use it, so it lacks a strong exclusion but is above implied usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a comprehensive URL analysis report including security scan results and key relationships (communicating files, contacted domains/IPs, downloaded files, redirects, threat actors). Returns both the basic security analysis and automatically fetched relationship data.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that relationship data is automatically fetched, but does not elaborate on permissions, response format, potential delays, or any side effects. It is adequate but not rich in behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, with the first sentence clearly stating the tool's purpose. The second sentence lists specific report contents without unnecessary fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given a single parameter and no output schema, the description adequately outlines the return contents, including specific relationship types. It does not cover error conditions or formatting, but for this tool's simplicity it is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100% for the single 'url' parameter, so the schema already fully explains it. The description adds no additional parameter semantics beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a comprehensive URL analysis report including security scan results and key relationships. It distinguishes itself from sibling tools like get_url_relationship by explicitly listing the combined contents.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool: when a full report with both basic analysis and relationship data is needed. It does not explicitly mention alternatives or exclusions, but the presence of siblings like get_url_relationship and the phrase 'automatically fetched relationship data' provide clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.10get_domain_reportget_file_relationshipget_file_reportget_ip_relationshipget_ip_reportget_url_relationshipget_url_reportScored across 7 tools
Each tool targets a unique combination of resource type (URL, file, IP, domain) and action (report vs. relationship). The report and relationship tools are clearly separated, and descriptions explicitly state the purpose of each, so there is no ambiguity.
All tools follow the consistent pattern get_<resource>_<action>, where <resource> is url, file, ip, or domain, and <action> is report or relationship. The naming is uniform and predictable.
With 7 tools, the count is well-scoped for a read-only VirusTotal client. Each tool covers a distinct entity-action pair, and there is no redundancy or unnecessary bloat.
The tool set thoroughly covers retrieval of reports and relationships for URLs, files, and IPs, plus domain reports. However, it lacks the ability to submit new files or URLs for scanning, a core VirusTotal workflow, and there is no dedicated domain relationship tool (though the report can include relationships). These are notable gaps.
VirusTotal MCP — file / URL / domain / IP reputation (BYO key)
VirusTotal reports for files, URLs, domains and IPs, plus file submission and analysis recovery.
Submit files and URLs to a malware sandbox, poll scans, fetch reports, hashes and IOCs.
Enrich, search, assess, and manage threat intelligence through 80+ typed MCP tools.
