Owasp Wstg RAG
OWASP Web Security Testing Guide RAG system with ChromaDB, MCP for Claude Code
Installation
npx owasp-wstg-ragAsk AI about Owasp Wstg RAG
Powered by Claude Β· Grounded in docs
I know everything about Owasp Wstg RAG. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
OWASP WSTG RAG
A Retrieval-Augmented Generation (RAG) system that indexes the OWASP Web Security Testing Guide (WSTG) into a vector database, providing instant access to security testing methodologies via REST API and MCP (Model Context Protocol) for Claude Code integration.
Features
- Complete WSTG Coverage - All 12 WSTG testing categories indexed and searchable
- Semantic Search - Find relevant testing methodologies using natural language queries
- MCP Integration - Direct integration with Claude Code for AI-assisted penetration testing
- REST API - HTTP endpoints for programmatic access
- WSTG ID Lookup - Retrieve complete test cases by WSTG identifier (e.g.,
WSTG-INPV-05)
WSTG Categories
| Category | WSTG ID | Description |
|---|---|---|
| Information Gathering | WSTG-INFO | Fingerprinting, enumeration, mapping |
| Configuration | WSTG-CONF | Server/platform configuration testing |
| Identity Management | WSTG-IDNT | User registration, account provisioning |
| Authentication | WSTG-ATHN | Login, password policy, MFA testing |
| Authorization | WSTG-ATHZ | Privilege escalation, IDOR, access control |
| Session Management | WSTG-SESS | Session tokens, cookies, fixation |
| Input Validation | WSTG-INPV | SQLi, XSS, command injection, SSTI |
| Error Handling | WSTG-ERRH | Error messages, stack traces |
| Cryptography | WSTG-CRYP | TLS, encryption, hashing |
| Business Logic | WSTG-BUSL | Workflow bypass, file upload |
| Client-Side | WSTG-CLNT | DOM XSS, clickjacking, WebSockets |
| API Testing | WSTG-APIT | REST, GraphQL, API security |
Quick Start
1. Install Dependencies
cd RAG_runner
pip install -r requirements.txt
2. Build the Database
python3 build_database.py
This will:
- Parse all OWASP WSTG HTML files
- Create semantic chunks for retrieval
- Build the ChromaDB vector database
3. Start the Server
python3 -m server.http_server
Server runs on http://localhost:5004
4. Test the API
# Health check
curl http://localhost:5004/health
# Search for SQL injection testing
curl -X POST http://localhost:5004/search \
-H "Content-Type: application/json" \
-d '{"query": "SQL injection testing methodology"}'
# Get specific WSTG test case
curl http://localhost:5004/wstg/WSTG-INPV-05
REST API Endpoints
| Endpoint | Method | Description |
|---|---|---|
/health | GET | Health check |
/info | GET | Database statistics |
/list | GET | List all documents |
/categories | GET | List categories and WSTG IDs |
/doc/{id} | GET | Get document by ID |
/wstg/{id} | GET | Get all chunks for WSTG ID |
/search | POST | Semantic search |
Search Request Body
{
"query": "SQL injection testing",
"n_results": 5,
"category": "input_validation",
"wstg_id": "WSTG-INPV-05"
}
Claude Code Integration (MCP)
Add to ~/.claude.json:
{
"mcpServers": {
"owasp-wstg-rag": {
"command": "python3",
"args": ["/path/to/OWASP_WSTG_Rag/RAG_runner/server/mcp_client.py"],
"env": {
"WSTG_RAG_URL": "http://localhost:5004"
}
}
}
}
MCP Tools
| Tool | Description |
|---|---|
search_wstg | Search WSTG for testing methodologies |
search_test_methodology | Search for how-to testing guides |
search_test_objectives | Search for test objectives |
get_wstg_test_case | Get complete test case by WSTG ID |
get_wstg_document | Get document by ID |
list_wstg_categories | List all categories and WSTG IDs |
wstg_health | Health check |
wstg_info | Database statistics |
Example Usage in Claude Code
# Search for SQL injection testing methodology
search_wstg("SQL injection testing methodology")
# Get specific test case
get_wstg_test_case("WSTG-INPV-05")
# Search within a category
search_wstg("authentication bypass", category_filter="authentication")
# Get test objectives for IDOR
search_test_objectives("IDOR insecure direct object reference")
Project Structure
OWASP_WSTG_Rag/
βββ README.md
βββ CLAUDE.md # Claude Code project guide
βββ raw_data/ # OWASP WSTG HTML source files
β βββ 01-Information_Gathering/
β βββ 02-Configuration_and_Deployment_Management_Testing/
β βββ 03-Identity_Management_Testing/
β βββ 04-Authentication_Testing/
β βββ 05-Authorization_Testing/
β βββ 06-Session_Management_Testing/
β βββ 07-Input_Validation_Testing/
β βββ 08-Testing_for_Error_Handling/
β βββ 09-Testing_for_Weak_Cryptography/
β βββ 10-Business_Logic_Testing/
β βββ 11-Client-side_Testing/
β βββ 12-API_Testing/
βββ RAG_runner/
βββ build_database.py # Main build pipeline
βββ requirements.txt
βββ parsers/
β βββ wstg_parser.py # HTML parser for WSTG
βββ chunking/
β βββ chunker.py # Semantic chunking
βββ server/
β βββ vector_store.py # ChromaDB wrapper
β βββ http_server.py # REST API server
β βββ mcp_client.py # MCP tools for Claude Code
βββ data/
βββ processed/ # Intermediate JSON files
βββ chroma_db/ # Vector database
Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β OWASP WSTG HTML Files β
β (raw_data/*.html) β
ββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β wstg_parser.py β
β Parse HTML β Structured JSON β
ββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β chunker.py β
β Create Semantic Chunks for RAG β
ββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββ
β
βΌ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β ChromaDB Vector Store β
β (data/chroma_db/) β
ββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββ
β
ββββββββββββββββ΄βββββββββββββββ
βΌ βΌ
ββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββ
β http_server.py β β mcp_client.py β
β REST API :5004 β β MCP for Claude Code β
β β β β
β GET /health β β search_wstg() β
β GET /info β β get_wstg_test_case() β
β GET /wstg/{id} β β search_test_methodology β
β POST /search β β list_wstg_categories() β
ββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββ
Use Cases
AI-Assisted Penetration Testing
Integrate with Claude Code to get instant access to OWASP testing methodologies during security assessments:
User: "How do I test for SQL injection?"
Claude: [Queries WSTG RAG]
β Returns WSTG-INPV-05 methodology with:
- Test objectives
- Step-by-step testing procedures
- Example payloads
- Tools to use
Automated Security Testing
Use the REST API to integrate WSTG methodologies into automated security pipelines:
import requests
# Get testing methodology for current test
response = requests.post('http://localhost:5004/search', json={
'query': 'session fixation testing',
'n_results': 3
})
methodology = response.json()['results']
Security Training
Quick reference for security testing methodologies during training or CTF challenges.
Requirements
- Python 3.8+
- ChromaDB
- BeautifulSoup4
- httpx
- MCP SDK (for Claude Code integration)
License
This project uses content from the OWASP Web Security Testing Guide, which is licensed under Creative Commons Attribution-ShareAlike 4.0.
Related Projects
- OWASP WSTG - Source material
- Claude Code - AI coding assistant with MCP support
- ChromaDB - Vector database for embeddings
