MCP Servers

styx-mcp

Provides 7 reverse-engineering tools (hexdump, disasm, strings, xref, Ghidra decompilation, angr symbolic execution, OLLVM deobfuscation) for LLM agents like hermes-agent and Claude Desktop.

README

Styx MCP

冥河。二进制是彼岸，逆向是渡河。

MCP stdio server exposing 7 reverse-engineering tools for LLM agents (hermes-agent, Claude Desktop, etc.).

Tools

Tool	Description	Dependency
`hexdump`	Hex dump + magic detection + Shannon entropy	(stdlib)
`disasm`	Capstone linear disassembly + function boundary detection	`capstone`
`strings`	Multi-encoding (ASCII/UTF-16LE/UTF-8) string extraction + classification	(stdlib)
`xref`	Cross-reference analysis: call-graph overview + per-address callers/callees/string refs	`capstone`
`ghidra`	Ghidra headless decompiler — C pseudocode	Ghidra binary
`angr`	Symbolic execution: CFG extraction / explore / avoid	`angr` (optional)
`deobfuscate`	OLLVM control-flow flattening recovery via PyGhidra	`pyghidra` (optional)

Install

# Minimal — hexdump, disasm, strings, xref
pip install styx-mcp

# With angr
pip install styx-mcp[angr]

# With PyGhidra (deobfuscate)
pip install styx-mcp[pyghidra]

# Everything
pip install styx-mcp[all]

Ghidra tool requires Ghidra headless: pacman -S ghidra (Arch) or download from ghidra-sre.org.

Usage

hermes-agent

# config.yaml
mcp_servers:
  styx:
    command: ["python", "-m", "styx.mcp_server"]

Claude Desktop

{
  "mcpServers": {
    "styx": {
      "command": "python",
      "args": ["-m", "styx.mcp_server"]
    }
  }
}

Standalone

python -m styx.mcp_server

Python API

from styx.tools.hexdump import hexdump
from styx.pipeline import run_pipeline

result = hexdump("/bin/ls")
print(result["output"])

# Batch pipeline
result = run_pipeline("/bin/ls", ["hexdump", "disasm", "strings", "xref"])

Protocol

JSON-RPC 2.0 over stdin/stdout (MCP stdio transport). Each tool returns:

{
  "success": true,
  "error": null,
  "output": "...",
  "discovered_nodes": [],
  "discovered_edges": [],
  "hypothesis_updates": []
}

License

MIT

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured