Forensic Artifact Investigator MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EVIDENCE_ROOT | Yes | Absolute path to the folder containing your evidence files | |
| VOLATILITY_BINARY | Yes | Absolute path to the Volatility binary (e.g., /path/to/vol) | |
| VIRUSTOTAL_API_KEY | No | Optional API key for VirusTotal reputation checks. Leave empty to skip online checks. | |
| MAX_RETURNED_STRINGS | No | Maximum number of strings to return | 5000 |
| VOLATILITY_TIMEOUT_MS | No | Timeout in milliseconds for Volatility commands | 300000 |
| FILE_COMMAND_TIMEOUT_MS | No | Timeout in milliseconds for the file command | 60000 |
| MAX_STRING_OUTPUT_BYTES | No | Maximum bytes of string output | 2000000 |
| VOLATILITY_MAJOR_VERSION | Yes | Version of Volatility (e.g., 3) | 3 |
| VOLATILITY_MAX_OUTPUT_BYTES | No | Maximum bytes of Volatility output | 5000000 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract-metadataA | Extract metadata from a forensic evidence file. Runs the real |
| extract-stringsA | Extract readable strings from a forensic evidence file using the real GNU |
| analyze-memory-dumpA | Analyze a Windows memory dump using the installed Volatility binary. Runs Volatility plugins sequentially: windows.info (OS/kernel details), windows.pslist (process list), windows.netscan (network connections), and windows.malfind (injected/code-hinting regions). Each plugin result independently reports success, failure, or unavailability — a single plugin failure does not fail the entire analysis. Designed for Windows memory dumps because the required plugins are Windows-specific. A malfind result requires analyst review — it is an indicator, not proof of malware. No forensic results are fabricated; if Volatility cannot parse the dump, real failure output is returned. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| full-file-analysis | Generate a structured forensic analysis workflow for a given evidence file. Instructs the model to call the appropriate tools (extract-metadata, extract-strings, or analyze-memory-dump), look up threat intelligence, and report findings under exactly three headings: Confirmed Anomalies, Possible Anomalies, and Clean. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Magic Bytes Reference | A reference table mapping common file extensions to their expected MIME types, magic byte signatures, and descriptions. Used internally by extract-metadata for MIME/extension comparison. This is reference documentation, not a substitute for command execution. |
| Analysis Log | The append-only chain-of-custody log recording every tool invocation. Each entry includes a UTC timestamp, tool name, target file, brief result summary, success status, and execution duration. No secrets or API keys are logged. Returns recent entries in JSONL format. |
| Threat Intelligence | Look up a file hash (MD5, SHA-1, or SHA-256) against threat intelligence. The EICAR test hash (MD5: 44d88612fea8a8f36de82e1278abb02f) returns a deterministic fixture response without any network call. Other hashes require VIRUSTOTAL_API_KEY to be set — without it, a "not configured" response is returned (no network call). With an API key, the hash is looked up via VirusTotal v3 API and only last_analysis_stats are summarized. This resource is identified as signatures://threat-intel. |
| Health Checks | Current health status of all registered health checks |
| Analysis Report | UI component for Analysis Report |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/guyoverclocked/forensic-artifact-investigator'
If you have feedback or need assistance with the MCP directory API, please join our Discord server