API Reference — Kovral.ai

Quick Start

Choose Your Language

Kovral proxies the OpenAI API — any existing OpenAI SDK integration works immediately.

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.kovral.ai/v1",
    api_key=os.environ["OPENAI_API_KEY"],
    default_headers={"X-Kovral-Key": os.environ["KOVRAL_API_KEY"]}
)

# Exact same call as before — Kovral inspects transparently
response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Summarize this document: ..."}]
)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.kovral.ai/v1',
  apiKey: process.env.OPENAI_API_KEY,
  defaultHeaders: { 'X-Kovral-Key': process.env.KOVRAL_API_KEY }
});

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello' }]
});

curl https://api.kovral.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-Kovral-Key: $KOVRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'

import "github.com/openai/openai-go"

client := openai.NewClient(
    option.WithBaseURL("https://api.kovral.ai/v1"),
    option.WithAPIKey(os.Getenv("OPENAI_API_KEY")),
    option.WithHeader("X-Kovral-Key", os.Getenv("KOVRAL_API_KEY")),
)

API Endpoints

Available Endpoints

POST /v1/chat/completions OpenAI-compatible chat — inspected and passed through

POST /v1/messages Anthropic-compatible messages — inspected and passed through

GET /v1/scan/status Check scan result for a given request_id

POST /v1/policies Create a new policy

GET /v1/policies List all policies

PUT /v1/policies/:id Update a policy

DELETE /v1/policies/:id Delete a policy

GET /v1/events Stream threat events (SSE)

GET /v1/stats Aggregated request and threat statistics

GET /v1/discovery/tools List discovered AI tools across your organization

Response Headers

Every Response Includes Security Metadata

HTTP/1.1 200 OK
X-Kovral-Request-Id: req_9k2x7mnapq
X-Kovral-Risk-Score: 12          # 0–100, higher = more risk
X-Kovral-Threats: []             # list of detected threat types
X-Kovral-Policy: allow           # allow | block | redact | alert
X-Kovral-Latency-Ms: 1.4         # Kovral processing time in ms
X-Kovral-Data-Classes: []        # detected sensitive data categories

Social Proof

Trusted by Security Teams Worldwide

From Fortune 500 CISOs to fast-growing AI startups — teams protecting AI at scale choose Kovral.

★★★★★

"Kovral gave us our first real-time view into every AI tool running inside our bank. We found 34 unsanctioned models in the first 48 hours. The posture score is now a standing item on my CISO dashboard."

Marcus Reid

VP Security Engineering · Tier-1 Bank

★★★★★

"Our EU AI Act readiness went from 'we don't know' to a documented compliance posture in three weeks. The use case registry and automated evidence collection saved our team months of manual work."

Priya Nair

Chief Compliance Officer · HealthTech SaaS

★★★★★

"The AI Firewall blocked a live indirect prompt injection attack on our customer-facing agent within the first week of deployment. Zero code changes, 1.8ms added latency. It's the easiest security win I've had in years."