attackforge-mcp
Connects AI assistants to AttackForge's Self-Service API with full endpoint coverage, response size optimization, and local caching for efficient use in long conversations.
README
attackforge-mcp
An MCP server that connects AI assistants (Claude, etc.) to the AttackForge Self-Service API (SSAPI).
vs. the official AttackForge MCP
AttackForge publishes an official MCP server. It exposes a limited subset of
the SSAPI — specifically: whoami, get_file, count_projects,
count_vulnerabilities, count_writeups, find_affected_assets,
find_projects, find_writeups, find_vulnerabilities, and
get_field_structure.
This server covers the full SSAPI and adds a layer of context efficiency on top, designed specifically for use inside long AI conversations:
| Official MCP | attackforge-mcp | |
|---|---|---|
| API coverage | 10 endpoints | Full SSAPI |
| Response passthrough | Raw API JSON | Slimmed (see below) |
| HTML fields | Returned | Stripped globally (−40–60% size) |
| List responses | Full objects | Summary projection + total/has_more envelope |
| Static data (form configs, testsuite library, project index) | Re-fetched every call | SQLite cache with TTLs |
| Cache management | — | cache tool (stats, invalidate) |
| Escape hatch | — | raw_request for any unlisted endpoint |
Why it matters: Large tool responses dump hundreds of lines of JSON into context on every call. Over a multi-step engagement that context fills up fast. By stripping HTML duplicates, projecting summary fields, and caching data that never changes mid-engagement, this server keeps each tool response as small as possible without losing information.
Setup
Requirements
- Python 3.12+
- uv
Install
git clone https://github.com/unstrike/attackforge-mcp
cd attackforge-mcp
uv sync
Configuration
Set two environment variables before starting the server:
| Variable | Description | Default |
|---|---|---|
AF_HOSTNAME |
Your AttackForge instance hostname | (required) |
X_SSAPI_KEY |
Your SSAPI key | (required) |
Run
AF_HOSTNAME=your.attackforge.com X_SSAPI_KEY=your-key uv run attackforge-mcp
Or add to your MCP client config (e.g. Claude Desktop claude_desktop_config.json):
{
"mcpServers": {
"attackforge-mcp": {
"command": "uv",
"args": ["run", "--directory", "/path/to/attackforge-mcp", "attackforge-mcp"],
"env": {
"AF_HOSTNAME": "your.attackforge.com",
"X_SSAPI_KEY": "your-key"
}
}
}
}
Tools
| Tool | What it does |
|---|---|
projects |
List, get, create, update, clone, archive projects and notes |
vulnerabilities |
List, get, create, update, bulk-create vulnerabilities |
testsuites |
Browse and manage the testsuite library |
testcases |
List, assign, update test cases on a project |
assets |
Manage project and library assets |
remediation |
Create and update remediation notes on vulnerabilities |
reports |
Generate and retrieve project reports |
analytics |
Failed testcases, vulnerable assets, common vulnerabilities |
utils |
Markdown → rich text conversion; form config lookup |
cache |
Inspect and invalidate the local SQLite cache |
raw_request |
Direct access to any SSAPI endpoint |
See CLAUDE.md for usage patterns.
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.
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.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.