AI-powered MCP server for dynamic malware analysis with Frida instrumentation, session-based debugging, and 46+ security tools
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"nexuscore": {
"env": {
"RUST_LOG": "info",
"CAPE_API_URL": "http://127.0.0.1:8000"
},
"args": [],
"command": "C:\\Path\\To\\NexusCore_MCP\\target\\release\\nexuscore_mcp.exe"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
NexusCore MCP is an advanced Model Context Protocol (MCP) server specifically designed for AI-driven dynamic malware analysis. It bridges the gap between Large Language Models (LLMs) like Claude/GPT-4 and low-level system instrumentation, enabling AI agents to actively debug, inspect, and analyze evasive malware in real-time.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'frida-tools' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked frida-tools against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ai-ml / security
Persistent memory using a knowledge graph
Dynamic problem-solving through sequential thought chains
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
MCP Security Weekly
Get CVE alerts and security updates for Nexuscore_MCP and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
English | 한국어
NexusCore MCP is an advanced Model Context Protocol (MCP) server specifically designed for AI-driven dynamic malware analysis. It bridges the gap between Large Language Models (LLMs) like Claude/GPT-4 and low-level system instrumentation, enabling AI agents to actively debug, inspect, and analyze evasive malware in real-time.
Why NexusCore? Traditional sandboxes give you a static report. NexusCore allows an AI agent to interactively manipulate malware execution—bypassing anti-debugging checks (Themida/VMProtect) via Frida, dumping memory, and performing forensic triage on the fly.
graph TD
A["AI Agent (Claude/Cursor)"] -- "MCP Protocol (Stdio)" --> B["NexusCore MCP Server"]
subgraph "Core Analysis Engine"
B -- "Persistent DB" --> C[("Sled Cache / Job Queue")]
B -- "Large Data" --> D["StreamManager (Dumps)"]
B -- "Observability" --> E["OpenTelemetry (Jaeger)"]
end
subgraph "SOTA Analysis Tools"
B -- "Micro-Emu" --> F["Unicorn Engine"]
B -- "Ref Bridge" --> G["Ghidra/IDA/x64dbg"]
B -- "Py Sandbox" --> H["AI Decryptor Tester"]
B -- "Self-Correction" --> I["YARA Verifier"]
end
subgraph "Host OS (Virtualized)"
B -- "Inject" --> J["Frida Engine (Stealth)"]
B -- "API" --> K["External (DIE, Capa, PE-Sieve)"]
end
| Tool | Description | Innovation |
|---|---|---|
micro_emulate | Executes isolated code snippets/functions. | Zero-Execution Analysis |
sync_reversing_data | Bridges AI findings directly to Ghidra/IDA. | Live Tool Sync |
test_decryptor | Safe sandbox for AI-generated Python decryptors. | Custom Logic Reversing |
verify_yara | Autonomously verifies YARA rules against samples. | Self-Correction Loop |
read_memory_chunk | Handles GB-scale memory dumps in chunks. | Context Window Optimization |
| Tool | Description | Key Tech |
|---|---|---|
spawn_process | Spawns process via Frida spawn, optionally injects stealth hooks. Use resume_process to continue. | Frida |
api_monitor | Monitors Windows API calls (Registry, Network, Files). | Frida |
dump_ssl_keys | Hooks libraries to dump keys for HTTPS decryption. | Frida |
generate_yara | Auto-generates initial YARA signatures. | Native |
scan_pe_sieve | Detects process hollowing and DLL injection. | PE-Sieve |
die_scan / capa_scan | High-speed static analysis with Sled caching. | DIE / CAPA |
src/tools/malware/debug/)| Tool | Description |
|---|---|
session_start | Start persistent cdb.exe debug session (headless). |
session_command | Send single command to active session. |
session_batch | Send multiple commands at once. |
session_end | Terminate debug session. |
debug_help | Common cdb.exe command reference. |
src/tools/common/frida_session.rs)| Tool | Description