Solutions / AI BuildersFor AI BuildersFor AI Adopters
For AI Builders · Ship governed, day one

Ship the agent. Pass the security review the same afternoon.

Three lines of SDK and every tool call your agent makes is authenticated, policy-matched, and written to a complete audit trail. No DSL to learn, no YAML to maintain: define policy in a form, hand your security team a log, and get back to building.

3lines to govern an agent
Minimalin-line gateway overhead
day 1security review, not week 6
agent.tsgoverned
// 1. one import
import { Igris } from "@igris-security/sdk";

const igris = new Igris({ apiKey: process.env.IGRIS_KEY });

// 2. one governed connection per user
const mcp = await igris.connect("github-prod", {
  user: "dev@acme.com",
  metadata: { role: "developer" },
});

// 3. every call is now policy-checked
await mcp.call("repo.read", { repo: "acme/api" });
await mcp.call("repo.delete", { repo: "acme/api" });
repo.read(acme/api)0.4msALLOW
repo.delete(acme/api)0.3msDENY
From zero to governed

Three commands. Then you're shipping behind a policy.

No sidecar to deploy, no proxy to stand up. The SDK runs in-process with a local policy cache, so the decision happens at the call boundary in microseconds, and the audit write is fire-and-forget.

01Install the SDK

One package for your whole agent. TypeScript, Python, and Go ship from the same spec, plus a REST API for everything else.

$ bun add @igris-security/sdk
# bun add v1.x done
# ✓ ready
02Open a governed connection

Bind a connection to the current user and their role. Igris resolves identity and loads the matching policy before the first call.

const mcp = await igris.connect(
  "github-prod",
  { user, metadata: { role } }
);
// → policy v.412 loaded
03Call tools like normal

Your agent code doesn't change. Every call() is matched, credentialed, and logged; denials come back as typed errors.

await mcp.call("repo.read", args);
// → ✓ allow · 0.4ms · audited
await mcp.call("repo.delete", args);
// → ✕ McpDenyError
One SDK, three guarantees

The same platform your CISO trusts. Wrapped in an API you actually want to use.

Sentinel, Guard, and Lens are one install for you and three boxes ticked for security. You write product code; the platform handles the tool calls, the prompts, and the paper trail.

GovernIgris Sentinel

Wrap your tool calls without rewriting your agent.

Sentinel is the chokepoint between your agent and every MCP server it touches. Identity, policy match, credential injection, audit: all inline, all in under a millisecond.

developer · repo.readALLOW
developer · repo.writeALLOW
developer · repo.deleteDENY
agent · stripe.chargeALERT
guest · db.writeDENY
ProtectIgris Guard

An LLM firewall you don't have to build.

Point your model traffic at Guard and prompt injection, PII leakage, and policy-violating responses get caught pre-flight. Your agent keeps its full reasoning when the traffic is clean.

prompt · SSN patternREDACT
prompt · injection sigBLOCK
prompt · "summarize…"PASS
response · AKIA keyBLOCK
response · cleanPASS
ObserveIgris Lens

The audit log that ends the security review.

Every decision streams to Lens: user, role, tool, args hash, latency, verdict. Filter it, replay any trace, export to your SIEM. Hand your security team a link instead of a meeting.

trace a4f9c2 · replay
filter · verdict=deny412
export · json / csv
stream · splunkLIVE
retention · 365d
What you get out of the box

Built for the team writing the agent. Not the team auditing it.

Six things you'd otherwise build yourself (auth plumbing, secret handling, a policy UI, an audit pipeline), shipped as one SDK and one dashboard.

01

Three-command quickstart

Install, connect, call. The SDK is in-process with a local policy cache, so you get governance without standing up a proxy or a sidecar.

time to first governed call< 5 min
infra to deploynone
agent code changed3 lines
02

Per-developer virtual keys

Real credentials stay in the vault. Each developer and each agent gets a scoped virtual key; revoke one without rotating the upstream secret.

real tokens in your code0
scope per keytool · env · rate
revoke propagation200ms
03

Form-based policy builder

Compose rules in the dashboard: role, tool glob, condition, decision. No DSL, no YAML, no policy language to learn or review in a PR.

tool: delete_*✕ deny
model: gpt-4*✓ allow
amount > $50alert
04

Replay & export the audit trail

Filter the log by user, tool, verdict, or trace ID. Replay any decision step-by-step. Export JSON or CSV, or stream the whole thing to your SIEM.

queryable fields12
trace replay✓ step-by-step
exportjson · csv · webhook
05

Local ↔ prod parity

The same policy runs against your dev key as your prod key. Catch a denial on your laptop, not in the incident channel. Dry-run any rule before you push it.

dev / prod policyidentical
dry-run rules
fail modeclosed by default
06

Works with your framework

MCP-native, and a thin wrapper for the stacks you already use. Drop it under LangChain, LlamaIndex, the Vercel AI SDK, or raw tool-calling.

MCP servers✓ native
LangChain · LlamaIndex✓ adapter
Vercel AI SDK✓ adapter
Why teams move faster

Security review used to be the bottleneck. Now it's a link.

The policy is already enforced and the audit is already on, so "is this approved?" stops being a meeting. Most teams collapse a multi-week review per agent into a same-day sign-off.

Before Igris

A review per agent. Every time.

6 wksper agent

  • Hand-rolled auth and secret handling in every service
  • Security reads code, asks for changes, re-reads
  • No audit trail; evidence assembled by hand
  • Shadow agents ship without anyone signing off
With Igris

Policy's already there. Ship today.

same dayto sign-off

  • Deny-by-default the moment the SDK is in
  • Form-based policy reviewers read in minutes
  • Complete audit exported as evidence on demand
  • One dashboard shows every agent already in scope
FAQ

Questions, answered.

Ready when you are

Three lines now. Deny-by-default from minute one.

Drop the SDK in, define a policy in the dashboard, and hand your security team a link instead of a launch blocker. Start in the docs or book a walkthrough.

  • 3 lines : install, connect, call
  • Minimal : in-line overhead
  • Virtual keys : real secrets never in your code
  • Form-based policy : no DSL, no YAML
  • Apache-2.0 SDK : self-host on Enterprise