Orihime vs Jadx AI MCP

In-depth architectural comparison of the Orihime and Jadx AI MCP MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

Which MCP Server Should You Choose?

Choose Orihime when:

• You need dedicated capabilities in the Security domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: No auth required (Free / Open Source).
• Primary tools included: Cross-repository code knowledge graph, Java, Kotlin, JavaScript, and TypeScript indexing, Embedded KuzuDB storage.

Explore Orihime Details

Choose Jadx AI MCP when:

• You need dedicated capabilities in the Security domain.
• You prefer local stdio subprocess transport architecture.
• Your security boundary fits: No auth required (Free / Open Source).
• Primary tools included: Exposes selected JADX-GUI classes over MCP, Retrieves Java source and smali code, Lists project classes, methods, and fields.

Explore Jadx AI MCP Details

Feature & Specification Comparison

Specification	Orihime srinivasan-sundaresan95 Security	Jadx AI MCP zinja-coder Security
Summary	Cross-repository code knowledge graph MCP server for Java, Kotlin, JavaScript, and TypeScript. Indexes source into embedded KuzuDB via tree-sitter; 30+ tools for call-flow tracing, multi-hop taint analysis (OWASP/CWE/PCI/STIG reports), entry-point reachability filtering, performance hotspot detection, and license compliance — without reading source files. 95% fewer tokens vs source-reading baseline. pip install orihime	JADX-AI-MCP is a plugin and MCP Server for the JADX decompiler that integrates directly with Model Context Protocol (MCP) to provide live reverse engineering support with LLMs like Claude.
Category & Scope

Tools & Capabilities Breakdown

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

{
  "mcpServers": {
    "srinivasan-sundaresan95-orihime": {
      "command": "uvx",
      "args": [
        "orihime"
      ]
    }
  }
}

{
  "mcpServers": {
    "zinja-coder-jadx-ai-mcp": {
      "command": "uvx",
      "args": [
        "httpx"
      ]
    }
  }
}

Related MCP Server Comparisons