---
title: Agent gateway | Qventis One
description: Coding agents run the tests a change affects and read the evidence through MCP, under your policy, with every call audited and no self-approval.
---

[Skip to content](https://qventis.ai/platform/agent-gateway#main)

[![qventis](https://qventis.ai/hubfs/raw_assets/public/qventis-one/images/qventis-logo.svg)![qventis](https://qventis.ai/hubfs/raw_assets/public/qventis-one/images/qventis-logo-reverse.svg)](https://qventis.ai/?hsLang=en)

- Platform
  
  [**Qventis One**The autonomous quality platform. Learn your app once, assure every kind of quality, decide in one view.](https://qventis.ai/one?hsLang=en)
  
  [**Qventis Engine**Plain English in, zero AI tokens at run time](https://qventis.ai/engine?hsLang=en) [**App Model**Learn your app once, reuse it everywhere](https://qventis.ai/one/app-model?hsLang=en) [**Quality View**One pane of glass for every release](https://qventis.ai/one/quality-view?hsLang=en) [**Studio**Anyone can automate in plain English](https://qventis.ai/platform/studio?hsLang=en)
  
  [**Trust & security**AI on your terms, people approve](https://qventis.ai/platform/trust?hsLang=en) [**Agent gateway**Coding agents run tests under policy](https://qventis.ai/platform/agent-gateway?hsLang=en) [**Integrations**Fits your CI, ALM and chat tools](https://qventis.ai/platform/integrations?hsLang=en) [**Editions**Start small, grow into One](https://qventis.ai/editions?hsLang=en)
  
  How it works[1Learn your app](https://qventis.ai/one/app-model?hsLang=en)[2Write plain English](https://qventis.ai/platform/studio?hsLang=en)[3Run every engine](https://qventis.ai/engine?hsLang=en)[4Decide in one view](https://qventis.ai/one/quality-view?hsLang=en)
- Engines
  
  [**Every kind of quality, one flow**Eight engines share one model of your app and report into one view.](https://qventis.ai/one?hsLang=en)
  
  [**Functional**Web, API, desktop and mobile](https://qventis.ai/engines/functional?hsLang=en) [**Performance**Speed budgets on real journeys](https://qventis.ai/engines/performance?hsLang=en) [**Security**Roles, sessions and exposure](https://qventis.ai/engines/security?hsLang=en) [**Service virtualization**Test before every API is ready](https://qventis.ai/engines/virtualization?hsLang=en)
  
  [**Test data**Safe, ready data for every run](https://qventis.ai/engines/test-data?hsLang=en) [**Data & ETL**Numbers that match end to end](https://qventis.ai/engines/data-etl?hsLang=en) [**Visual**Catch what users would see](https://qventis.ai/engines/visual?hsLang=en) [**Accessibility**WCAG checks with an audit trail](https://qventis.ai/engines/accessibility?hsLang=en)
  
  Packaged-app packs[Oracle](https://qventis.ai/engines/packaged-apps?hsLang=en)[SAP](https://qventis.ai/engines/packaged-apps?hsLang=en)[Salesforce](https://qventis.ai/engines/packaged-apps?hsLang=en)[Workday](https://qventis.ai/engines/packaged-apps?hsLang=en)[See all packs](https://qventis.ai/engines/packaged-apps?hsLang=en)
- Solutions
  
  [**Release in confidence**Certify every vendor upgrade and configuration change before your business feels it.](https://qventis.ai/platforms?hsLang=en)
  
  Enterprise platforms
  
  [Salesforce](https://qventis.ai/platforms/salesforce?hsLang=en)[SAP](https://qventis.ai/platforms/sap?hsLang=en)[Oracle](https://qventis.ai/platforms/oracle?hsLang=en)[Workday](https://qventis.ai/platforms/workday?hsLang=en)[ServiceNow](https://qventis.ai/platforms/servicenow?hsLang=en)[Dynamics 365](https://qventis.ai/platforms/dynamics-365?hsLang=en)[nCino](https://qventis.ai/platforms/ncino?hsLang=en)[Coupa](https://qventis.ai/platforms/coupa?hsLang=en)
  
  [**Industries**Banking, insurance, healthcare and more](https://qventis.ai/industries?hsLang=en)
  
  By need
  
  [**Release testing**Run only what a change affects](https://qventis.ai/solutions/release-testing?hsLang=en) [**Legacy desktop**Apps automation never reached](https://qventis.ai/solutions/legacy-desktop?hsLang=en) [**Quality CoE**One standard across the business](https://qventis.ai/solutions/quality-coe?hsLang=en)
  
  Certify an upgrade[1Release notes in](https://qventis.ai/platforms?hsLang=en)[2Impact on your app](https://qventis.ai/one/app-model?hsLang=en)[3Run in sandbox](https://qventis.ai/engine?hsLang=en)[4Sign off](https://qventis.ai/one/quality-view?hsLang=en)
- [Customers](https://qventis.ai/customers?hsLang=en)
- Company
  
  [**About qventis**Why we built one platform](https://qventis.ai/about?hsLang=en) [**Blog**Field notes on quality, AI and agents](https://qventis.ai/blog?hsLang=en) [**Trust center**How we protect your data](https://qventis.ai/platform/trust?hsLang=en) [**Contact**Talk to a person, not a bot](https://qventis.ai/contact?hsLang=en)
  
  Prefer email?[contact@qventis.ai](mailto:contact@qventis.ai)

[Book a demo](https://qventis.ai/contact#demo)

[Qventis One](https://qventis.ai/one?hsLang=en)/Platform

# Agents ship faster Your test gate still holds

Claude Code, Copilot and Cursor run the tests their change affects through MCP. Your policy decides what each may do, and no agent approves itself.

[Book a demo](https://qventis.ai/contact#demo)[See Trust & security](https://qventis.ai/platform/trust?hsLang=en)

- Agents run impacted tests
- No agent approves itself
- Every call audited

| The agent asks | The gateway answers |
| --- | --- |
| Which tests cover my checkout change? | The tests in 'checkout' the change affects |
| Run them on the test environment | All but one passed |
| Show me the failure | Expected '38.00', saw '42.00', screenshot attached |
| Fix the test | Proposal queued for a person to approve |

## What agents can do

### Find impacted tests

Get the tests a change affects, ranked by risk, or look them up by component, screen or tag.

### Run and read evidence

Runs are deterministic and use zero AI tokens. Agents read step logs, screenshots and what each check expected and saw.

### Propose heals

Agents suggest a fix with evidence attached. Each proposal waits for a person to approve.

## Security built into every call

The flowFrom change to approval

IdentityScoped sign-in per agent

PolicyChecked on every call

AuditEvery call on record

Three doorsCLI, HTTP API and MCP

### An agent verifies a change

A coding agent finishes a change and checks whether it broke anything. Every step is checked against policy.

- Signs in with its own scoped token
- Finds and runs the tests its change affects
- Reads the evidence and proposes a heal
- A person approves or rejects the heal

[Read: coding agents need a test gate](https://qventis.ai/blog/agents-need-a-test-gate?hsLang=en)

### Sign-in and allow-lists

Agents sign in with SSO and OAuth through your identity provider. You decide which actions each may take, and where.

- Scoped access for each agent
- Allow-lists per project
- Anything not on the list is denied

[See Trust & security](https://qventis.ai/platform/trust?hsLang=en)

### Policy and approvals

Each call is checked against role and attributes, the same way a person's request would be.

- Deleting tests needs a person
- Changing suites or shared components needs approval
- No agent approves a heal, including its own

[Read: earned autonomy for AI in testing](https://qventis.ai/blog/earned-autonomy?hsLang=en)

### Every call audited

Who asked for what, with which inputs and what result, exported to your SIEM.

- The same audit trail as people
- Runs tied to the change behind them
- Results in the same Quality View

[See Quality View](https://qventis.ai/one/quality-view?hsLang=en)

### Three doors, one policy

People, pipelines and agents reach the platform in different ways. The rules behind each door are the same.

- CLI for engineers and CI jobs
- HTTP API for pipelines, portals and scripts
- MCP for coding and chat agents

[See integrations](https://qventis.ai/platform/integrations?hsLang=en)

## Questions

Which agents work with it?

Any agent that speaks MCP, including Claude Code, GitHub Copilot and Cursor. CI pipelines use the CLI or HTTP API under the same policy.

Does an agent spend AI tokens when it runs tests?

Only its own, deciding what to call. The test run itself uses zero AI tokens.

Can we limit an agent to one project?

Yes. Per-project allow-lists decide what an agent may do and where.

## Leave with one agent gated by policy

See one agent connected to one project, running tests under your policy.

[Book a demo](https://qventis.ai/contact#demo)

![qventis](https://qventis.ai/hubfs/raw_assets/public/qventis-one/images/qventis-logo-reverse.svg)

Qventis One is the autonomous quality platform from qventis.ai. Learn your app once. See every kind of quality in one place. Change nothing without your approval.

[contact@qventis.ai](mailto:contact@qventis.ai)

## Platform

- [Qventis One](https://qventis.ai/one?hsLang=en)
- [Qventis Engine](https://qventis.ai/engine?hsLang=en)
- [App Model](https://qventis.ai/one/app-model?hsLang=en)
- [Quality View](https://qventis.ai/one/quality-view?hsLang=en)
- [Studio](https://qventis.ai/platform/studio?hsLang=en)
- [Agent gateway](https://qventis.ai/platform/agent-gateway?hsLang=en)
- [Editions](https://qventis.ai/editions?hsLang=en)

## Engines

- [Functional](https://qventis.ai/engines/functional?hsLang=en)
- [Performance](https://qventis.ai/engines/performance?hsLang=en)
- [Security](https://qventis.ai/engines/security?hsLang=en)
- [Service virtualization](https://qventis.ai/engines/virtualization?hsLang=en)
- [Test data](https://qventis.ai/engines/test-data?hsLang=en)
- [Data & ETL](https://qventis.ai/engines/data-etl?hsLang=en)
- [Visual](https://qventis.ai/engines/visual?hsLang=en)
- [Accessibility](https://qventis.ai/engines/accessibility?hsLang=en)

## Solutions

- [Enterprise platforms](https://qventis.ai/platforms?hsLang=en)
- [Industries](https://qventis.ai/industries?hsLang=en)
- [Legacy desktop](https://qventis.ai/solutions/legacy-desktop?hsLang=en)
- [Release testing](https://qventis.ai/solutions/release-testing?hsLang=en)
- [Quality CoE](https://qventis.ai/solutions/quality-coe?hsLang=en)

## Company

- [About](https://qventis.ai/about?hsLang=en)
- [Customers](https://qventis.ai/customers?hsLang=en)
- [Blog](https://qventis.ai/blog?hsLang=en)
- [Trust center](https://qventis.ai/platform/trust?hsLang=en)
- [Contact](https://qventis.ai/contact?hsLang=en)
- [Legal](https://qventis.ai/legal?hsLang=en)

© 2026 qventis.ai. All rights reserved.Product names of third-party platforms are trademarks of their owners.