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 |
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 |
|---|---|
| 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 |
TDQS
Scored across 3 tools
Each tool addresses a completely distinct forensic task: file metadata/hash, string extraction with indicator scanning, and memory dump analysis. There is no functional overlap, so agents can easily select the right tool.
All tool names follow the same verb-noun pattern with lowercase and hyphens (extract-metadata, extract-strings, analyze-memory-dump). The naming is perfectly consistent and predictable.
Three tools is on the lower end but still within a reasonable range for a focused forensic artifact investigator. The count is just slightly under what might be expected, but each tool covers a major area.
The toolset covers core forensic workflows: file metadata/hash analysis, string/indicator extraction, and memory dump analysis. Minor gaps exist (e.g., no timeline or registry parsing), but the essential artifact types are addressed.