quality-assurance
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
quality-assurance
Pixi-first quality assessment MCP server: lint, type-check, security, complexity, baselines and trend analysis behind a lean 3-meta-tool interface.
Overview
quality-assurance is an MCP server (package src/quality_assurance) that runs quality tooling through pixi and returns compact, structured results. The lean server (quality_assurance.lean_server) exposes only discover_tools, get_tool_spec and execute_tool to keep client context small; the HTTP transport (quality_assurance.http_lean_server) serves it on port 4106 at http://127.0.0.1:4106/mcp.
Tools reachable through execute_tool:
Assessment:
quality_execute_lint_assessment,quality_execute_typecheck_assessment,quality_execute_security_scan,quality_execute_complexity_analysis,quality_execute_comprehensive_suiteAnalysis:
quality_calculate_quality_score,quality_generate_recommendations,quality_detect_quality_patterns,quality_prioritize_issuesBaselines and trends:
quality_establish_baseline,quality_compare_against_baseline,quality_analyze_trendsFixes and reports:
quality_apply_automated_fixes,quality_generate_comprehensive_reportPixi integration:
quality_execute_pixi_aware_assessment,quality_optimize_pixi_environment,quality_generate_pixi_tasks,quality_validate_pixi_integrationHealth:
quality_get_system_health
Related MCP server: glintefy
Development
This project is pixi-only; the package installs itself editable via [tool.pixi.pypi-dependencies]. Do not use pip or uv directly.
pixi install -e ci
# Tests (use -e py312 / -e py313 for a specific interpreter)
pixi run test
# Lint + type-check + tests
pixi run -e ci quality
# Start the HTTP MCP server (port 4106)
pixi run http-serverAvailable Tasks
Task | Environment | Description |
| all | Run the test suite on the selected environment's interpreter |
|
| Run |
|
| Ruff critical rules / all rules / auto-fix |
|
| Ruff format / verify formatting |
|
| mypy over |
| default | Tests with coverage (runs in |
|
| bandit, safety and radon |
|
| Build the distribution |
| default | Start the HTTP MCP server (port 4106) |
| default | Start the lean stdio MCP server |
| default | Start the full stdio MCP server |
Run pixi task list -e <env> for the complete list.
Branch model
Feature, fix and chore branches open PRs into
developmentonly.Only
developmentmay open a PR intomain; the Branch Policy check enforces this.Required checks: CI Success (plus Branch Policy on PRs to
main).No direct pushes to
developmentormain.
License
MIT License - see LICENSE for details.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
30+ deterministic dev and delivery tools: linting, metrics, diagrams, model advice, AI-text checks.
Scan, fix and justify your application code until it is approved to ship.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceProvides comprehensive code quality tools including linting, security scanning, TypeScript checking, and testing through a single MCP server. Integrates multiple quality analysis tools like Biome, ESLint, and Playwright for streamlined development workflows.-
- AlicenseNot gradedqualityAmaintenanceProvides comprehensive code quality analysis and automated fixing, available as a CLI and MCP server (currently in early beta with MCP part untested).1MIT
- AlicenseCqualityBmaintenanceAgentic code-quality CLI and stdio MCP server that runs real Python and JS/TS quality engines (Ruff, pytest, ESLint, Prettier, Vitest, etc.) for linting, testing, and reviewing code.79MIT
- AlicenseAqualityDmaintenanceProvides 28 MCP tools across 16 analysis engines for comprehensive Python code quality assessment, including complexity scoring, security scanning, dead code detection, dependency auditing, and test quality analysis.2816 PyPIMIT