Developer documentation

Integrate, configure, and deploy DFENS.

DFENS is an application firewall for LLM traffic, the engine built in the ai-firewall repository. It inspects prompts, model responses, and tool-result content against declarative rules. Start with DFENS Cloud — sign up and get an endpoint in minutes, nothing to deploy. Running it yourself, on your own hardware or in your VPC, is also available as an Enterprise-tier deployment, covered by the rest of this section — but Cloud is the fastest path for almost everyone. Same rule engine, same request and response schemas, either way.

Private registry

The self-hosted container image is distributed through a private registry to approved Enterprise customers and design partners; it is not on any public registry yet. Request access to be issued a registry credential and an image reference; the examples below use REGISTRY/ai-firewall:<tag> as a placeholder for it.

01 · Start here

DFENS Cloud

What signup gives you, the X-AI-Firewall-Key header, Cloud-specific error responses, and your customer portal. The fastest way to a working endpoint — sign up on portal.dfens.ai.

02 · Integrate

API integration

Two integration paths: the transparent reverse proxy and the in-app /v1/inspect endpoint. Request and response schemas, block behaviour, and streaming semantics. Applies to Cloud and self-hosted alike.

03 · Claude Code & Desktop

Claude clients

Point Claude Code at DFENS with two environment variables, or deploy Claude Desktop in third-party inference mode across a fleet — MDM configuration keys and the credential-helper gotcha.

04 · Configure — Enterprise only

Configuration

Enterprise self-hosted only. The YAML schema, environment-variable overrides, upstream auth modes, providers, audit, and metrics, with the defaults that ship in the image.

05 · Deploy — Enterprise only

Deployment

Enterprise self-hosted only. From a single docker run to Docker Compose to a hardened Kubernetes manifest set. Probes, state, and the network isolation the proxy requires.

Reference

OWASP LLM Top 10

What the default rule set detects, mapped to the 2025 OWASP LLM Top 10, on the main site.

How it fits into your stack

There are two ways to put DFENS in the path of a model call, and they share one rule engine and one audit log:

Reverse proxy. DFENS speaks the OpenAI and Anthropic wire formats (plus Azure OpenAI, AWS Bedrock, and Google Gemini/Vertex on their native routes). Point your SDK's base URL at DFENS and every request, response, and tool call is inspected transparently. No code changes.
In-app inspection. When you can't sit a proxy in the network path, call POST /v1/inspect from your own code with a prompt, a response, or a tool result, and act on the allow/deny verdict it returns.

Read this first

Secure the data plane on two layers. DFENS can require callers to present a client token (the X-AI-Firewall-Key header, see client authentication), and it's still meant to run on a trusted network segment (private network, or a Kubernetes NetworkPolicy). Treat these as defense-in-depth: turn on the client token and keep the listener off untrusted networks. Client auth is opt-in, so if you haven't configured a token the proxy accepts any caller that can reach it.

Start with DFENS Cloud: sign up at portal.dfens.ai and send your first blocked request in minutes, no deployment required. Need it inside your own boundary instead? That's the Enterprise path — read Deployment and Configuration to get a self-hosted instance running.