◆ The Igris Security Platform
Three Products.
One Complete AI Security Platform.
Igris Security provides the essential infrastructure to secure, govern, and observe every layer of your AI systems — from real-time MCP gateway governance, to LLM conversation protection in production.
59+
LLM Providers Supported
Deny-by-Default
Policy Engine
<1ms
Gateway Overhead
Real-Time
Anomaly Detection
Igris Sentinel
Runtime MCP Governance
Igris Sentinel is the industry's first SDK-first governance platform for the Model Context Protocol (MCP). Sit between your AI agents and every MCP server they connect to. Enforce RBAC policies with metadata conditions, inject upstream credentials securely, block unauthorized tool calls in real time, and log every interaction — all with a single SDK function call.
import { Igris } from "@igris/sdk";
const igris = new Igris({ apiKey: "ig_..." });
const config = igris.getMcpConfig("vk_github", {
user: "alice@company.com",
metadata: { role: "developer" },
});
// Works with any MCP client
const client = new McpClient({
transport: new StreamableHttp(config.url, {
headers: config.headers,
}),
});Igris Guard
LLM Firewall & Conversation Protection
Igris Guard sits transparently between your users and any LLM — OpenAI, Anthropic Claude, Google Gemini, or a self-hosted model. Every user prompt is inspected before it reaches the model; every LLM response is validated before it reaches the user. Apply content policies, prevent PII leakage, block prompt injection attacks, and enforce per-user controls — without switching LLM providers or refactoring your application.
{
"name": "Content safety policy",
"model": "gpt-4o",
"rules": [
{
"type": "prompt",
"action": "block",
"conditions": { "contains_pii": true }
},
{ "type": "response", "action": "redact" }
]
}Individually Powerful. Together Unstoppable.
All three Igris Security products share a common telemetry layer. Sentinel governance events and Guard firewall decisions flow into Igris Lens. Your security posture gets stronger with every product you add.
Prevent
Igris Sentinel blocks unauthorized MCP calls before they reach upstream servers.
Detect
Igris Guard inspects every prompt and response, enforces content policies, and acts as your LLM content guard.
Monitor
Igris Lens gives 24/7 visibility into every AI interaction across the entire stack.
Report
Generate audit-ready compliance documentation from Igris Lens with one click.
Igris Lens
CISO Dashboard & Unified Observability
Igris Lens turns raw AI security events into actionable intelligence. It centralizes every policy decision, tool call, prompt, response, and anomaly from Igris Sentinel and Igris Guard into one high-fidelity audit trail. Executives get risk heatmaps. Compliance teams get one-click PDF reports. Security engineers get trace-level debugging.
Unified Log Stream
Unified log stream from all Igris Security products.
Executive Risk Heatmaps
Executive risk heatmaps across departments and AI sub-systems.
Immutable Audit Trails
Immutable 1-click audit trails verified for compliance investigations.
Automated PDF Reports
Automated PDF report generation for compliance and security audits.
Real-Time Anomaly Alerting
Real-time anomaly alerting via Slack, email, and webhooks.
SIEM Integration
SIEM integration: export logs via webhooks, REST API, or streaming.
Policy Decisions
Real-Time
Anomaly Alerts
Instant
Log Retention
3 Years
Report Export
One-Click PDF
What You See in Lens
◆ Platform FAQ
Technical Deep Dive
Common questions about the Igris Security platform architecture.
SDK Integration Targets
Integrate governance into any application built with modern frameworks
Ready to Govern Your AI?
Join teams using Igris to enforce runtime policies and maintain full visibility over their AI operations.