# Silmaril Firewall API

**Canonical:** https://apis.io/apis/silmaril/silmaril-firewall-api/  
**Provider:** Silmaril — https://apis.io/providers/silmaril/  
**Base URL:** https://firewall-mcp.silmaril.dev  
**Documentation:** https://silmaril.dev/docs

Silmaril Firewall API is published by [Silmaril](https://apis.io/providers/silmaril/) on the [APIs.io](https://apis.io/) network. Tagged areas include AI Firewall, Runtime Security, and Prompt Injection. The published artifact set on APIs.io includes API documentation and an API reference.

AI application firewall classify API. A Firewall client sends each sanitized classification input (user input, tool response, model output, or system prompt) with a hook label and optional tool name to a tenant-issued classify endpoint, and receives a prediction (BENIGN/MALICIOUS), a primary outcome, and score/threshold data. Credentials and the classify endpoint are issued by Silmaril (not self-serve). A companion hosted, read-only MCP evidence server exposes firewall findings to agents.

## Machine-readable artifacts (3)

- **Documentation** — https://silmaril.dev/docs
- **APIReference** — https://silmaril.dev/docs
- **APIsJSON** — https://raw.githubusercontent.com/api-evangelist/silmaril/refs/heads/main/apis.yml

## Tags

AI Firewall, Runtime Security, Prompt Injection

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/apis/silmaril/silmaril-firewall-api/). The API's provider profile, Kin Score and agent-readiness rating are at https://apis.io/providers/silmaril/.