MCP server

Give your coding agent the context
to build without breaking what works.

Qarmiq’s MCP server lets supported AI coding tools access project knowledge, scenarios, and defects, so agents can work with existing product expectations and verification findings.

See Qarmiq in action All features
The real thing

An agent with the context before it writes.

The agent asks what the project is, finds what exists, then proposes a change that waits for confirmation.

  • Read project and defect context, ask for suggested scenarios, file defects and create runs
  • Every write is planned, confirmed and logged, and nothing can be deleted through it
  • API keys are scoped to read, authoring or execution

Where it stands. Any AI coding tool that supports MCP should connect. We confirm each named tool live before claiming it.

you    Add coverage for refunds after a partial shipment

agent  orient            what is this project?
agent  find “refund”     1 scenario, 2 open defects
agent  explain SHOP-D1  evidence and developer brief
agent  author_scenario  planned, awaiting confirmation

you    confirm
agent  author_scenario  written, and logged

Illustrative example. Writes are planned, confirmed and logged.

In practice

What it does.

01

Context before code.

An agent can inspect existing scenarios, understand open defects, and review how behavior is verified before proposing new checks or making changes through supported actions.

02

Bring product findings into the coding workflow.

Give your coding agent access to relevant evidence and developer briefs, so it can start investigating from what happened rather than guessing at the problem.

03

Keep actions controlled and auditable.

Access keys can be scoped to reading, authoring, or execution. Writes are planned, confirmed, and logged, and deletion isn’t available through the MCP server.

Why a finding should reach the editor

The fix starts from what happened.

A coding agent that can read the evidence does not have to guess what the failure was.

Context before code

The agent can see existing scenarios, open defects and how a scenario is tested before it writes anything.

Writes you can audit

Each write is planned and confirmed before it happens, and logged afterwards.

Nothing destructive

Deleting is not possible through the server, whatever the key allows.

Where it fits

It works with the rest.

Defects and briefs

Every bug should come with a clear next step.

Defects carry severity, status, duplicates and attachments, linked to the scenario, check and run where they were found. An AI developer brief turns the captured evidence into something an engineer or a coding agent can act on.

See Defects and briefs → Scenarios and checks

Define what your product must always get right.

A scenario states one thing that must always be true, in a single sentence. Its checks say what must be verified to prove it. Nothing in them is a click or a selector, so a redesign does not invalidate them.

See Scenarios and checks → Zoe

Ask your product quality data a question.

Zoe is an in-app assistant that answers questions about your project’s runs, scenarios and quality data. She can draft a defect or a run for a person to submit, but never changes anything herself.

See Zoe →

Connect your coding agent to your product’s quality context.

We will connect a coding tool to a real project and show you how much context it gets.

See Qarmiq in action All features

Qarmiq is not self-serve yet, so we set each team up directly. Pricing is one flat price per project.