Reference

Deep technical reference for engineers integrating with IntentGate. API surface, deployment architecture, and integration recipes for common SIEM and observability stacks.

For decision makers

IntentGate Product Brief

Executive overview: the authorization pipeline, what ships, architecture, compliance mapping (AI Act Annex IV, DORA, GDPR, NIST AI RMF, SOC 2), OWASP for LLM and Agentic AI, pricing, and pilot terms. Built to forward to a CFO, CISO, or Risk Committee.

Request the brief PDF · 17 pages

For customers, login required

Customer documentation portal

The full deployment set: install and getting-started guides, the Operator Manual, Operations Runbook, Operating Model, and the operating processes (actor swimlanes and RACI). Dedicated customer work, provided behind a login when you start a pilot.

Open the docs portal → Login required

API

API reference

Every endpoint the gateway exposes. Runtime path (/v1/mcp, /v1/tool-call) plus admin path (capabilities, policies, audit, approvals, tenants). Authentication, error codes, request and response shapes.

Architecture

Architecture

What runs where, what talks to what. Components, request lifecycle, audit chain, multi-tenant model, three deployment topologies, trust boundaries.

MCP firewall capabilities

Firewall capabilities

The controls the MCP firewall enforces at runtime, schema sanitizer, intent enforcement, runtime limits and circuit breakers, kill switch, credential brokering, deception, session rewind, and proof-of-intent. Each with a diagram.

Integrations

Recipes for common enterprise topologies. Each page is vendor-agnostic and links to deployable artifacts in the gateway repo.

AWS + Microsoft Sentinel

AWS workloads · Sentinel SIEM

Audit events into Microsoft Sentinel (hot lane, 12 months) and Amazon S3 + Athena (cold lane, multi-year). Native sinks, Glue table DDL, KQL query pack.

OPEN SOURCE CORE

Gateway

Self-hosted authorization service. Go binary, embedded OPA, multi-tenant, tamper-evident audit chain.

CLIENT LIBRARIES

SDKs

Agent-side libraries. Issue, attenuate, present capability tokens. Byte-compatible between Python and TypeScript.

  • pip install intentgate

    Python 3.10–3.13. PyPI · GitHub

  • npm install @intentgate-app/intentgate

    Node 18+, dual ESM/CJS, zero runtime deps. GitHub

DOCUMENTATION

Install in three steps

Standard Helm. About three minutes.

  1. Generate two secrets

    One signs tokens, one gates the admin API.

  2. Helm install the chart

    Gateway, extractor, Postgres-backed audit. No CRDs.

  3. Verify the four checks

    One health endpoint confirms the pipeline is live.

DOCUMENTATION

Mint your first token

One credential per agent. Issued by the gateway.

  1. Define the agent's identity

    Subject, tenant, and the tools it's allowed to call.

  2. Set the budget

    TTL, max calls, optional cost ceiling.

  3. Hand it to your agent

    Shown once. Stored like any secret. Revocable any time.

Want the commands? GitHub for source.

Getting-started guides

Four end-to-end runnable guides in the open-source gateway repo. Each is a single milestone you'll hit when bringing IntentGate into your environment. Copy-paste from a fresh laptop.

01 · 5 min

Quickstart, gateway running in 5 minutes

One docker run in-memory, mint a token, watch the capability check fire on a tool the token doesn't grant. The shortest path from zero to seeing a real authorization decision.

02 · 15 min

Your first Rego policy

Write Rego, push it via /v1/admin/policies/drafts + promote, test allow / escalate / block paths against the live engine. Includes the dry-run pattern and common rule shapes (time-of-day, per-agent overrides, step-up required).

03 · 15 min

Wire your first agent (Python SDK)

pip install intentgate, three-line Gateway() construction, typed exception per check. The LLM-loop-with-error-feedback pattern and attenuate() for sub-agent delegation.

04 · 10 min

Querying audit and verifying the chain

GET /v1/admin/audit filter parameters, SOC playbook queries (blocks in last hour, all activity by agent), chain verify endpoint, the daily-evidence-pack pattern for SOC 2 CC7.2 and EU AI Act Article 12.

Browse all guides on GitHub →

What's not (yet) in the guides above

The four guides cover the developer and SOC paths end-to-end: zero to a working policy, a wired-up agent, and queryable audit. For production deployment patterns, Helm-based HA, monitoring + alerting, day-2 operations, incident playbooks, full environment variable reference, the 23-page deployment runbook is the canonical document.

Request the runbook PDF