Radare2 Hatchery
Scanned 5/29/2026
Install via CLI
openskills install plurigrid/asi---
name: radare2-hatchery
description: Radare2 Hatchery
version: 1.0.0
---
# Radare2 Hatchery
---
name: radare2-hatchery
description: MCP server for radare2 binary analysis integration with AI assistants. Decompilation, disassembly, and reverse engineering via MCP protocol.
trit: -1
color: "#D6DB4C"
---
## Overview
**radare2-mcp** provides an MCP server enabling Claude and other AI assistants to perform binary analysis using radare2.
## Features
- **Direct stdin/stdout communication** - Simple MCP transport
- **Binary analysis tools** - Full radare2 capabilities
- **AI assistant integration** - Seamless Claude Desktop support
- **File exploration** - Inspect any binary format
- **Decompilation** - Pseudocode generation via r2ghidra
## Installation
```bash
# Via r2pm (radare2 package manager)
r2pm -Uci r2mcp
```
## Configuration
### Claude Desktop
Edit `~/Library/Application Support/Claude/claude_desktop_config.json`:
```json
{
"mcpServers": {
"radare2": {
"command": "r2pm",
"args": ["-r", "r2mcp"]
}
}
}
```
### Docker
```bash
docker build -t r2mcp .
```
```json
{
"mcpServers": {
"radare2": {
"command": "docker",
"args": ["run", "--rm", "-i", "-v", "/tmp/data:/data", "r2mcp"]
}
}
}
```
## MCP Tools Available
The server exposes radare2 analysis via MCP:
- `open_file` - Open binary for analysis
- `analyze` - Run analysis at depth levels 0-4
- `decompile_function` - Get C-like pseudocode
- `list_functions` - Enumerate discovered functions
- `list_strings` - Extract strings from binary
- `xrefs_to` - Find cross-references
- `run_command` - Execute raw r2 commands
## Gay.jl Integration
```julia
# Rec2020 wide gamut learning
gay_seed!(0xe72b09cb7aebe913)
# Forward mode autodiff
∂params = Enzyme.gradient(Forward, loss, params, seed)
```
## Repository
- **Source**: TeglonLabs/radare2-mcp
- **Seed**: `0xe72b09cb7aebe913`
- **Index**: 55/1055
- **Color**: #b3a6b8
## GF(3) Triad
```
radare2-hatchery (-1) ⊗ mcp-builder (0) ⊗ gay-mcp (+1) = 0 ✓
```
## Related Skills
- `mcp-builder` - MCP server development
- `blackhat-go` - Security techniques
- `tree-sitter` - AST-based code analysisNo comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.