Skip to main content
Glama
Sentinel-One

Purple AI MCP Server

Official
by Sentinel-One

threat_intel_get_file_relationships

Extract network IOCs and file relationships from a file hash to pivot from malware samples to domains, IPs, and related files.

Instructions

Get relationships for a file hash from VirusTotal (network IOCs and related files).

This tool extracts relationship data from a file's VirusTotal analysis, revealing network infrastructure (domains, IPs, URLs) contacted by the file, as well as related files. This is essential for pivoting from files to network indicators and building comprehensive threat intelligence profiles.

Available relationship types:

  • contacted_domains: Domains contacted during execution

  • contacted_ips: IP addresses contacted during execution

  • contacted_urls: URLs contacted during execution

  • similar_files: Files with similar characteristics

  • execution_parents: Files that executed this file

  • bundled_files: Files bundled/dropped by this file

  • compressed_parents: Archives containing this file

  • overlay_parents: Parent files with overlays

What this tool provides:

  • Network infrastructure IOCs (domains, IPs, URLs)

  • File lineage and relationships

  • Dropped/bundled files

  • Similar malware samples

  • Execution chain information

Common Use Cases:

  • Extract network IOCs from malware samples

  • Build threat intelligence from file analysis

  • Pivot from files to domains/IPs for blocking

  • Identify related malware families

  • Map malware infrastructure and campaigns

  • Enrich incident response with related indicators

Args: hash_value: The file hash (MD5, SHA1, or SHA256) to query. relationship_type: The type of relationship to retrieve (e.g., 'contacted_domains').

Returns: JSON string containing: - relationships: Array of related objects with full details (up to 100) - count: Number of relationships found

Examples: hash_value="275a021bbfb6489e54d471899f7db9d1663fc695ec2fe2a2c4538aabf651fd0f", relationship_type="contacted_domains"

hash_value="44d88612fea8a8f36de82e1278abb02f",
relationship_type="contacted_ips"

Notes: - Requires a valid VirusTotal API key (PURPLEMCP_VT_API_KEY environment variable) - Returns up to 100 relationships (the API maximum) - Not all files have all relationship types - Relationship data comes from sandbox execution - Private API keys have access to more relationship types - When a hash or relationship is not found, returns a structured JSON response with found=false - IMPORTANT: Do NOT call this tool repeatedly with the same parameters. It returns the same data each time, not additional results.

Raises: ThreatIntelligenceClientError: If there's an error communicating with the API. RuntimeError: If the API key is not configured.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hash_valueYes
relationship_typeYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description fully discloses behaviors: returns up to 100 relationships, not all types available, sandbox execution source, private API keys have more, returns found=false on not found, idempotency warning, and error types. Very comprehensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with sections and bullet points, but slightly verbose. Could be trimmed without losing key information. Still efficient given the detail needed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all aspects: purpose, parameters with examples, return format, error handling, authentication, and usage constraints. Explains output structure (JSON with relationships and count). No gaps given complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (no property descriptions), but the description compensates fully by specifying hash format (MD5/SHA1/SHA256), relationship_type values with examples, and listing all available types. Adds significant meaning beyond bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves relationships for a file hash from VirusTotal, listing specific relationship types and use cases. It distinguishes from siblings like threat_intel_by_hash by focusing on relationships rather than general file intelligence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use cases such as extracting network IOCs and pivoting from files. Includes important note about not calling repeatedly with same params. Could be improved by mentioning when NOT to use this tool (e.g., use threat_intel_by_hash for general file analysis).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Sentinel-One/purple-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server