How do I use QA MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@QA MCP Server Analyze requirement for user login and generate test cases" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

QA MCP Server

by sanumenon

Overview Schema Related Servers Score Discussions

Python

Remote

QA MCP Server

An extensible Model Context Protocol (MCP) server designed to become a unified AI-powered QA platform.

Current Status

Phase 1 — Foundation & QA Intelligence

COMPLETED

Step	Capability	Status
1	Project foundation	COMPLETED
2	MCP server + health	COMPLETED
3	LLM provider abstraction	COMPLETED
4	Requirement Analyzer	COMPLETED
5	Test Case Generator	COMPLETED
6	Test Case Reviewer	COMPLETED
7	End-to-End QA Workflow	COMPLETED

Phase 2 — Project Context, Persistence, Versioning & Portability

Step	Capability	Status
1	QA Project Context	COMPLETED
2	SQLite Persistence	COMPLETED
3	QA Suite Versioning	COMPLETED
4	Import / Export	COMPLETED

1. Vision

The long-term goal is to build a reusable QA MCP platform exposing QA capabilities to MCP-compatible AI clients.

MCP Client / AI Assistant
          |
          v
      QA MCP Server
          |
   +------+------+------+
   |             |      |
   v             v      v
QA Intelligence Connectors Automation
   |             |      |
Analyze        Jira    UI
Generate       GitHub  API
Review         Slack   Mobile
                       Performance
          |
          v
       QA Agent
          |
          v
 Persistent QA Context
          |
          v
 Project / Requirement / Suite Versions
          |
          v
 Import / Export

2. Phase 1 Architecture

Requirement
     |
     v
Requirement Analyzer
     |
     v
RequirementAnalysis
     |
     v
Test Case Generator
     |
     v
TestCaseResponse
     |
     v
Test Case Reviewer
     |
     v
TestCaseReview
     |
     v
QASuiteResult

Core MCP capabilities:

analyze_requirement
generate_test_cases
review_test_cases
generate_qa_suite

3. LLM Architecture

LLMProvider
     |
     +---- MockLLM
     |
     +---- BedrockLLM

LLM access is provider-independent so the QA tools can be tested locally and later connected to AWS Bedrock or another provider.

AI output is validated using Pydantic models before downstream processing.

4. Phase 2 Step 1 — QA Project Context

Status: COMPLETED

A QA project contains:

QAProject
 |
 +-- project_id
 +-- name
 +-- description
 +-- application
 +-- environment
 +-- metadata

Core service:

ProjectContext
 |
 +-- create_project()
 +-- get_project()

MCP tools:

create_qa_project
get_qa_project

5. Phase 2 Step 2 — SQLite Persistence

Status: COMPLETED

Projects are persisted in:

data/qa_mcp.db

SQLite table:

qa_projects

Architecture:

ProjectContext
       |
       v
ProjectRepository
       |
       v
SQLiteProjectRepository
       |
       v
SQLite

The core context does not depend directly on SQLite.

Persistence was verified across separate Python processes.

6. Phase 2 Step 3 — QA Suite Versioning

Status: COMPLETED

QA requirements and generated suites are versioned and persisted independently.

Related MCP server: QTM4J MCP Server

Requirement versions

QA Project
   |
   +-- Requirement v1
   +-- Requirement v2
   +-- Requirement v3

Each requirement version contains:

version_id
project_id
version
requirement
application
environment
created_at

Versions are maintained independently per project.

Suite versions

Each suite records the requirement version that produced it:

Requirement v1
      |
      v
Suite v1

Requirement v2
      |
      v
Suite v2

Each suite version contains:

suite_id
project_id
requirement_version_id
version
test_cases
review
created_at

Architecture

core/
└── versioning/
    └── service.py
        |
        v
infrastructure/
└── versioning/
    ├── repositories.py
    └── sqlite_version_repository.py
        |
        v
      SQLite

The two versioning folders are intentional:

core/versioning contains business logic.
infrastructure/versioning contains repository interfaces and SQLite implementations.

Core services

QARequirementVersioningService
QASuiteVersioningService

Repository interfaces

RequirementVersionRepository
SuiteVersionRepository

SQLite implementations

SQLiteRequirementVersionRepository
SQLiteSuiteVersionRepository

MCP tools

Requirement:

create_requirement_version
get_requirement_version
list_requirement_versions

Suite:

create_suite_version
get_suite_version
list_suite_versions

7. Phase 2 Step 4 — Import / Export

Status: COMPLETED

The QA MCP server now supports portable project artifacts containing:

QA Project
    |
    +-- Requirement Versions
    |
    +-- Suite Versions

Export

The export flow is:

SQLite
   |
   +-- Project
   +-- Requirement Versions
   +-- Suite Versions
           |
           v
QAImportExportService
           |
           v
QAProjectExport
           |
           v
JSON

Export is based on persisted data, not caller-assembled objects.

MCP tool:

export_qa_project

Input:

project_id

Output:

{
    "project_id": "...",
    "export_version": "1.0",
    "payload": "..."
}

Import

The import flow is:

JSON
  |
  v
Parse
  |
  v
QAProjectExport validation
  |
  v
Relationship validation
  |
  v
Duplicate project check
  |
  v
SQLite persistence

MCP tool:

import_qa_project

Import validates:

Export JSON
Export structure
Project identity
Requirement → project relationship
Suite → project relationship
Suite → requirement-version relationship
Duplicate project protection

Existing projects are not silently overwritten.

Round-trip verification

The complete round trip has been verified:

SQLite DB A
    |
    v
EXPORT
    |
    v
JSON
    |
    v
IMPORT
    |
    v
SQLite DB B
    |
    v
Compare

Verified artifacts:

Project           ✅
Requirements      ✅
Suites            ✅
Relationships     ✅

Test isolation

MCP import/export tests use isolated temporary SQLite databases.

This prevents test execution from polluting:

data/qa_mcp.db

and allows repeated test execution without relying on previous test state.

P2-S4 verification baseline

Import/Export focused tests: 7 passed
MCP Import/Export tests:     2 passed
Full regression:            49 passed
Application-code warnings:   0
Known external warning:      1

The remaining warning is the known external pydantic_settings warning concerning the lifespan field's unresolved forward reference.

8. Project Structure

Current important source structure:

qa-mcp/
|
+-- src/
|   +-- qa_mcp/
|       |
|       +-- core/
|       |   +-- config.py
|       |   +-- llm.py
|       |   +-- project/
|       |   |   +-- context.py
|       |   |
|       |   +-- versioning/
|       |   |   +-- service.py
|       |   |
|       |   +-- import_export/
|       |       +-- service.py
|       |
|       +-- infrastructure/
|       |   +-- project_repository.py
|       |   +-- sqlite_project_repository.py
|       |   |
|       |   +-- versioning/
|       |       +-- repositories.py
|       |       +-- sqlite_version_repository.py
|       |
|       +-- models/
|       |   +-- schemas.py
|       |
|       +-- tools/
|       |   +-- requirement/
|       |   +-- testcase/
|       |   +-- workflow/
|       |
|       +-- server.py
|
+-- tests/
+-- config/
+-- data/
|   +-- qa_mcp.db
|
+-- README.md

9. Local Setup

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

Run tests:

pytest -q

Current verified baseline:

49 passed

Run the MCP server:

python -m qa_mcp.server

Verify server imports:

python -c "from qa_mcp.server import mcp; print('MCP server imports OK')"

10. Development Guidelines

We follow this workflow for every implementation step:

IMPLEMENT
    |
    v
FOCUSED TESTS
    |
    v
FULL REGRESSION
    |
    v
RUNTIME / MCP VERIFICATION
    |
    v
FIX / REFINE
    |
    v
MARK STEP COMPLETE
    |
    v
UPDATE README
    |
    v
DOWNLOAD NEW README CHECKPOINT
    |
    v
NEXT STEP

Rules:

Implement one step at a time.
Test every feature.
Existing tests must remain green.
No step is complete until locally verified.
Update README at every verified milestone.
Core business logic must remain independent of MCP transport.
Persistence and external integrations stay behind interfaces.
LLM providers remain replaceable.
AI output must be validated.
Tests must remain repeatable against persistent storage.
Do not delete persistent databases merely to make tests pass.
Use isolated databases for persistence-focused tests.
Do not manually copy assistant conversation into README.
The README is the authoritative development checkpoint.
No major feature is complete until its MCP/runtime path is verified.

11. Architectural Principles

Core business logic belongs in core.
Persistence belongs in infrastructure.
MCP transport belongs in server.py and MCP-facing tools.
Domain/data models belong in models.
Core services must not depend directly on SQLite implementations.
External integrations must be isolated behind interfaces.
LLM providers remain replaceable.
AI-generated output must be validated before downstream use.
Persistent data must not be confused with test fixtures.
Tests must be repeatable.
Import operations must validate relationships before persistence.
Imports must not silently overwrite existing projects.
Completed milestones require regression verification.
README updates are part of milestone completion.

12. Phase 2 Roadmap

Step	Capability	Status
1	QA Project Context	COMPLETED
2	SQLite Persistence	COMPLETED
3	QA Suite Versioning	COMPLETED
4	Import / Export	COMPLETED
5	Jira Connector	NEXT
6	Jira → QA Workflow	Planned
7	Automation Case Generator	Planned
8	QA Agent	Planned
9	GitHub / CI Integration	Planned
10	Internet Deployment	Planned

13. Planned Final Architecture

                    MCP CLIENT / AI ASSISTANT
                              |
                              v
                       +-------------+
                       |   QA MCP    |
                       |   Server    |
                       +------+------+
                              |
              +---------------+----------------+
              |               |                |
              v               v                v
        QA Intelligence   Connectors      Automation
              |               |                |
        +-----+-----+     +---+---+       +----+----+
        |     |     |     |   |   |       |    |    |
     Analyze Gen  Review Jira GitHub    UI   API  Perf
                                            Mobile
              |
              v
          QA Agent
              |
              v
       Persistent Context
              |
              v
     Project / Requirement
        / Suite Versions
              |
              v
       Import / Export

14. Current Baseline

Phase 1
  Steps 1–7  COMPLETED

Phase 2
  Step 1 — QA Project Context       COMPLETED
  Step 2 — SQLite Persistence       COMPLETED
  Step 3 — QA Suite Versioning      COMPLETED
  Step 4 — Import / Export          COMPLETED

Current verification:

49 tests passed
SQLite persistence verified
Requirement versioning verified
Suite versioning verified
Import/export contract verified
Import validation verified
Round-trip persistence verified
MCP import/export verified
MCP server imports successfully
Test isolation verified

Known warning:

pydantic_settings
IncompleteFieldDefinitionWarning
Field 'lifespan'

This is an external dependency warning and is not currently blocking functionality or tests.

15. Next Development Step

Phase 2 → Step 5
       |
       v
Jira Connector

The next phase of implementation should begin only after this README checkpoint has been retained.

16. Milestone History

Phase 1
  |
  +-- Foundation
  +-- LLM abstraction
  +-- Requirement analysis
  +-- Test generation
  +-- Test review
  +-- QA suite workflow
  +-- MCP integration
  |
  v
Phase 1 COMPLETE

Phase 2
  |
  +-- QA Project Context
  +-- SQLite Persistence
  +-- Requirement/Suite Versioning
  +-- Import / Export
  |
  v
Phase 2 Step 4 COMPLETE

This README represents the project state after successful verification of Phase 2 → Step 4 — Import / Export.

This server cannot be installed

license - not found

Not graded

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

qasphere-mcp
Testing & QA Tools Developer Tools
Hypersequent
A
license
A
quality
B
maintenance
QA Sphere MCP server that enables Large Language Models to interact directly with test management system test cases, supporting AI-powered development workflows and test case discovery.
Updated a month ago (2026-07-21 22:57 UTC)
15
101
23
MIT
QTM4J MCP Server
Testing & QA Tools Project Management App Automation
salehrifai42
A
license
A
quality
B
maintenance
An MCP server that exposes the QMetry Test Management for Jira Cloud REST API as tools for MCP-compatible clients. It enables users to manage test cases, test cycles, test executions, test plans, folders, and automation rules through natural language interactions.
Updated 2 months ago (2026-06-11 04:28 UTC)
30
57
MIT
TestOps MCP Server
Testing & QA Tools Project Management
syn7xx
A
license
B
quality
A
maintenance
Enables AI assistants to interact with TestOps 5.25 for managing projects, test runs, test plans, and test cases via MCP tools.
Updated 2 months ago (2026-06-27 12:29 UTC)
31
49
MIT
test-case-generator-ai-mcp
Testing & QA Tools Developer Tools
CSOAI-ORG
A
license
Not graded
quality
A
maintenance
Enables generation of test cases, edge cases, and test matrices for software testing, integrated with MCP protocol and EU AI Act compliance.
Updated a month ago (2026-07-26 09:32 UTC)
3
MIT

View all related MCP servers

Related MCP Connectors

Qase Test Management
Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
SmartBear MCP
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
mcp
Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sanumenon/qa-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

QA MCP Server

Current Status

Phase 1 — Foundation & QA Intelligence

Phase 2 — Project Context, Persistence, Versioning & Portability

1. Vision

2. Phase 1 Architecture

3. LLM Architecture

4. Phase 2 Step 1 — QA Project Context

5. Phase 2 Step 2 — SQLite Persistence

6. Phase 2 Step 3 — QA Suite Versioning

Requirement versions

Suite versions

Architecture

Core services

Repository interfaces

SQLite implementations

MCP tools

7. Phase 2 Step 4 — Import / Export

Export

Import

Round-trip verification

Test isolation

P2-S4 verification baseline

8. Project Structure

9. Local Setup

10. Development Guidelines

11. Architectural Principles

12. Phase 2 Roadmap

13. Planned Final Architecture

14. Current Baseline

15. Next Development Step

16. Milestone History

Maintenance

Resources

Looking for Admin?

Related MCP Servers

qasphere-mcp

QTM4J MCP Server

TestOps MCP Server

test-case-generator-ai-mcp

Related MCP Connectors

Latest Blog Posts

MCP directory API