Skip to main content
Glama
Sentinel-One

Purple AI MCP Server

Official
by Sentinel-One

threat_intel_by_hash

Query VirusTotal for threat intelligence on a file hash. Get detection results from 70+ antivirus engines, file metadata, and behavioral analysis to validate suspicious files or enrich IOCs.

Instructions

Get threat intelligence for a file hash from VirusTotal/Google Threat Intelligence.

This tool queries VirusTotal's database to retrieve comprehensive threat intelligence about a file based on its cryptographic hash. The hash can be in MD5, SHA1, or SHA256 format.

What this tool provides:

  • Malware detection results from 70+ antivirus engines

  • File metadata (size, type, names, creation dates)

  • Behavioral analysis results

  • YARA rule matches

  • Crowdsourced threat intelligence

  • Relationships with other files, URLs, domains, and IPs

  • Community comments and votes

  • Signature information (digital signatures, if present)

Common Use Cases:

  • Incident response: Validate if a suspicious file is malicious

  • Threat hunting: Research known malware samples

  • Malware analysis: Get context about a file before deeper investigation

  • IOC enrichment: Add threat intelligence to indicators of compromise

Args: hash_value: File hash in MD5, SHA1, or SHA256 format (case-insensitive).

Returns: JSON string containing comprehensive threat intelligence data including: - Detection statistics (e.g., 45/70 engines detected as malicious) - File attributes and metadata - Last analysis date and statistics - Community reputation score - Related threat intelligence - MITRE ATT&CK techniques (if applicable)

Examples: MD5: "44d88612fea8a8f36de82e1278abb02f" SHA1: "3395856ce81f2b7382dee72602f798b642f14140" SHA256: "275a021bbfb6489e54d471899f7db9d1663fc695ec2fe2a2c4538aabf651fd0f"

Notes: - Requires a valid VirusTotal API key (PURPLEMCP_VT_API_KEY environment variable) - Results are cached by VirusTotal and may not reflect real-time scans - File must have been previously submitted to VirusTotal to have results - Private API keys have higher rate limits and additional features

Not Found Response: When a hash is not found, returns a JSON response with this structure: { "found": false, "resource": "hash_value", "resource_type": "file", "message": "File hash 'hash_value' was not found in VirusTotal's database..." }

Raises: ThreatIntelligenceClientError: If there's an error communicating with the API (not for not-found cases). RuntimeError: If the API key is not configured.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hash_valueYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

No annotations provided, so the description carries full burden. It discloses caching behavior, API key requirement, rate limit differences, not-found response structure, and possible exceptions (ThreatIntelligenceClientError, RuntimeError). All behavioral traits are transparently documented.

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?

The description is well-structured with sections (intro, what it provides, use cases, args, returns, examples, notes, not found, raises). It is front-loaded with purpose. A bit lengthy but every section adds value; could be slightly more concise.

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?

Given the presence of an output schema, the description still explains the return structure in detail (detection stats, file metadata, etc.), covers prerequisites (API key), error conditions, and not-found case. It is fully complete for an agent to invoke this tool correctly.

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%, but the description thoroughly defines the hash_value parameter: accepted formats (MD5, SHA1, SHA256), case-insensitivity, and provides examples. This adds significant meaning beyond the 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 it retrieves threat intelligence for a file hash from VirusTotal/Google Threat Intelligence. It distinguishes from siblings by specifying hash-based lookup, while sibling tools handle domains, IPs, URLs, etc. The specific verb 'Get' and resource 'threat intelligence for a file hash' are unambiguous.

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

Usage Guidelines5/5

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

The description provides common use cases (incident response, threat hunting, etc.) and explicit notes: requires valid API key, file must have been previously submitted, results are cached, and private API keys have higher rate limits. It implicitly advises when to use this tool versus siblings like threat_intel_get_file_behavior for behavioral 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