documentation

brin adds realtime threat detection to your agent by scoring the context it is about to consume: a package, web page, MCP server, repo, or skill. you get a risk verdict and can block, warn, or proceed.

free API. no auth, no signup. cached results in under 50ms. if brin is unreachable, your agent keeps working as normal.

##get started

Quickstart

Add brin to your coding agent or your own agent stack — hooks, wrappers, API, CLI.

##API

API Overview

Entity types, verdicts, tolerance, response headers. No auth, no signup.

Endpoints

Every endpoint, parameter, and response shape. Artifact lookup, PR scanning, batch, search, graph.

CLI

A single command returns a score, verdict, and threats.

##concepts

How It Works

3-tier scanning pipeline, scoring dimensions, graph scoring.

Threat Detection

Agentic threats (prompt injection, tool shadowing) and supply chain attacks (install hooks, credential harvesting).

##integrations

Overview

All integrations grouped by type — coding agents, frameworks, email.