mem-forensics-mcp
Multi-tier memory forensics MCP server combining a fast Rust engine with Volatility3 coverage for analyzing memory dumps.
README
<img src="icon.png" width="150" alt="Memory forensics MCP">
mem-forensics-mcp
Unified Memory Forensics MCP Server - Multi-tier engine combining Rust speed with Vol3 coverage.
Architecture
Three-tier engine automatically routes each tool to the fastest backend:
LLM <-> [mem-forensics-mcp (Python)] <-> memoxide (Rust child, stdio MCP)
<-> Volatility3 (Python library)
| Tier | Engine | Speed | Coverage |
|---|---|---|---|
| Tier 1 | Rust (memoxide) | Fast | pslist, psscan, cmdline, dlllist, malfind, netscan, cmdscan, search, readraw, rsds |
| Tier 2 | Python analyzers | Medium | Process anomalies, C2 detection, credentials, YARA, VT integration |
| Tier 3 | Volatility3 | Slower | Any vol3 plugin (filescan, handles, svcscan, driverscan, ...) |
Installation
Prerequisites
# Install uv (fast Python package manager)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Ensure Python 3.10+
python3 --version
Install from PyPI
uv pip install mem-forensics-mcp
Install from source
git clone https://github.com/x746b/mem_forensics-mcp.git
cd mem_forensics-mcp
# Full install (recommended)
uv sync --extra full
# Minimal (Vol3 only, no YARA/VT)
uv sync --extra volatility3
Build Rust Engine (optional)
Prebuilt binaries ship for aarch64-linux and x86_64-linux in engines/memoxide/. The server auto-detects the host architecture. To build from source:
# Requires Rust toolchain (https://rustup.rs)
cd engines/memoxide-src
cargo build --release
# Binary lands at engines/memoxide-src/target/release/memoxide
# The server auto-detects it (prefers local build over prebuilt)
Configure Volatility3 (optional)
If Vol3 is installed at /opt/volatility3 it's auto-detected. Otherwise: export VOLATILITY3_PATH="/path/to/volatility3"
Verify
uv run python -m mem_forensics_mcp.server
# Should show: Rust engine: available, Volatility3: available
Adding to Claude CLI
claude mcp add mem-forensics-mcp \
--scope user \
-- uv run --directory /opt/mem_forensics-mcp python -m mem_forensics_mcp.server
With custom Volatility3 path:
claude mcp add mem-forensics-mcp \
--scope user \
-e VOLATILITY3_PATH=/opt/volatility3 \
-- uv run --directory /opt/mem_forensics-mcp python -m mem_forensics_mcp.server
Quick Start
# 1. Initialize
memory_analyze_image(image_path="/evidence/memory.raw")
# 2. Full triage
memory_full_triage(image_path="/evidence/memory.raw")
# 3. Drill down
memory_run_plugin(image_path="/evidence/memory.raw", plugin="malfind", pid=1234)
Tool Reference
Core
| Tool | Tier | Description |
|---|---|---|
memory_analyze_image |
1->2 | Initialize image, auto-detect profile |
memory_run_plugin |
1->3 | Run any plugin (Rust or Vol3) |
memory_list_plugins |
- | List available plugins |
memory_list_sessions |
- | List active sessions |
memory_get_status |
- | Show engine status |
Analysis
| Tool | Tier | Description |
|---|---|---|
memory_full_triage |
1+2 | Complete automated investigation |
memory_hunt_process_anomalies |
2 | DKOM detection, parent-child validation |
memory_get_process_tree |
2 | Process tree with suspicious highlighting |
memory_find_injected_code |
1->2 | Code injection + YARA scanning |
memory_find_c2_connections |
1+2 | Network C2 detection |
memory_get_command_history |
1+2 | Command recovery + classification |
memory_extract_credentials |
2 | Hash/secret extraction via Vol3 |
Extraction
| Tool | Tier | Description |
|---|---|---|
memory_dump_process |
2 | Process info and loaded DLLs |
memory_dump_vad |
2 | Examine memory region details |
memory_list_dumpable_files |
3 | List cached files |
Threat Intelligence
| Tool | Description |
|---|---|
vt_lookup_hash |
VirusTotal hash lookup |
vt_lookup_ip |
VirusTotal IP reputation |
vt_lookup_domain |
VirusTotal domain reputation |
vt_lookup_file |
Hash file + VT lookup |
Example: Full Triage Output
Running memory_full_triage on a Windows 10 memory dump (Win10 19041, x64, VMware):
{
"threat_level": "critical",
"risk_score": 100,
"summary": "Processes: 115 found. Process Anomalies: 4 info-level. Network: 4 flagged of 79 connections. Commands: 56 memory fragments. Injected Code: 12 RWX regions. Correlations: 2 critical.",
"engine": "rust+python"
}
Key findings:
| Category | Detail |
|---|---|
| Suspicious process | mmc.exe launched from explorer.exe, loading a .msc file from browser downloads |
| Injected code | 4 RWX private memory regions in mmc.exe, 2 in EXCEL.EXE |
| Child process | dllhost.exe spawned by mmc.exe with executable RWX region |
| Network | svchost.exe connections to external IPs on ports 443/80 |
| Correlations | active_implant + active_c2_session flagged as critical |
| IOCs | Suspicious external IPs extracted automatically |
Drill-down with filtered filescan:
memory_run_plugin(image_path="memory.raw", plugin="filescan", filter="notepad")
# Returns: 2 of 7612 results matched (server-side grep before truncation)
Related Projects
- winforensics-mcp — Windows disk forensics (EVTX, Registry, MFT, Prefetch, YARA, PCAP)
- mac_forensics-mcp — macOS DFIR (Unified Logs, FSEvents, Spotlight, Plists)
MIT License | xtk | Built for the DFIR community. No Windows required >) <!-- mcp-name: io.github.x746b/mem-forensics-mcp -->
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。