中文文档 | English

context1337 — AboutSecurity MCP Server

Standalone MCP resource service that turns AboutSecurity from a file repo into a consumable API. Like context7, but for security.

Quick Start

Docker (recommended)

# Default: clones AboutSecurity from GitHub automatically
make docker

# Use local AboutSecurity repo (skip git clone, faster rebuild)
make docker-local
# or specify path:
make docker-local ABOUTSECURITY_LOCAL=../AboutSecurity

# Pin to a specific branch/tag
make docker-ref ABOUTSECURITY_REF=dev

docker run -p 8088:8088 -e ABOUTSECURITY_API_KEY=your-key context1337:latest

Local Development (recommended for first-time users)

Only requires Go 1.25+ (gotip) and Python 3 installed on your machine.

git clone https://github.com/wgpsec/context1337.git
cd context1337

# One command does everything:
# 1. Clones AboutSecurity repo (if not already present)
# 2. Installs Python dependencies (jieba, pyyaml)
# 3. Builds FTS5 search index (builtin.db)
# 4. Compiles Go binary
# 5. Symlinks data directories
# 6. Starts the server
make run

# Build & run (requires data/ populated with builtin.db or AboutSecurity content)
make build
./absec serve --port 8088 --data-dir ./data  # default: --tool-mode lite

The server will be available at http://localhost:8088.

MCP Client Configuration

Claude Code (CLI)

# Add as user-level MCP server (available in all projects)
claude mcp add aboutsecurity --transport http --scope user http://localhost:8088/mcp

# Or project-level only (run from within your project directory)
claude mcp add aboutsecurity --transport http http://localhost:8088/mcp

If you set ABOUTSECURITY_API_KEY on the server, add the auth header:

claude mcp add aboutsecurity --transport http --header "Authorization: Bearer your-api-key" --scope user http://localhost:8088/mcp

After adding, restart Claude Code and run /mcp to verify the connection shows connected.

Claude Desktop

Edit your Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "aboutsecurity": {
      "url": "http://localhost:8088/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key"
      }
    }
  }
}

Cursor

{
  "mcpServers": {
    "aboutsecurity": {
      "serverUrl": "http://localhost:8088/mcp"
    }
  }
}

Usage Examples

Once connected, just ask your AI assistant naturally:

Search across all types

• "Search for SQL injection resources" → search_security(query="SQL injection") finds skills, payloads, and tools
• "What XSS payloads are available?" → search_security(query="XSS", type="payload")
• "List all scanning tools" → search_security(type="tool", category="scan")
• "Show me all exploit skills" → search_security(type="skill", category="exploit")

Get detailed knowledge

• "Explain the SQL injection skill in detail" → get_security_detail(name="sql-injection", type="skill", depth="full") includes references
• "Show me the nmap tool configuration" → get_security_detail(name="nmap", type="tool") returns YAML config

Read data files

• "Show the top 100 passwords dictionary" → read_security_file(path="Auth/password/Top100.txt", type="dict")
• "Get XSS event handler payloads" → read_security_file(path="XSS/events.txt", type="payload")

Search vulnerabilities

• "Find critical Apache vulnerabilities" → search_security(query="Apache", type="vuln", severity="CRITICAL")
• "List all middleware vulnerabilities" → search_security(type="vuln", category="middleware")
• "Get the Log4j RCE vulnerability details" → get_security_detail(name="CVE-2021-44228", type="vuln", depth="full")

The AI will automatically call the right MCP tools to find relevant security knowledge.

Available MCP Tools

Default mode is lite (3 tools). Use --tool-mode full for 15 per-type tools. If the AI model fails to invoke tools proactively, switch to full mode — the 15 fine-grained, domain-specific tools improve trigger rates.

Lite mode (default, 3 tools)

Full mode (15 tools)

Makefile Targets

REST API

Environment Variables

Architecture

Build time:   AboutSecurity/ → Python+jieba → builtin.db (FTS5 index)
Startup:      cp builtin.db → runtime.db, scan team/ → INSERT
Runtime:      MCP Streamable HTTP + REST API, pure Go tokenizer for new content