- Conduid
- Marketplace
- #code-quality
MCP servers tagged code-quality
201 live MCP servers tagged "code-quality", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with code-quality.
Code Quality MCP
MCP server for Python code quality analysis: flake8, mypy, McCabe, vulture
Antigravity Agents
Universal agentic engineering layer for Google Antigravity. Features autonomous multi-agent orchestration, epistemic grounding, 9 strict verification gates, AST blast radius analy…
Grasshopper Quality Analyzer
Automated quality analysis for Grasshopper definitions. Real-time lint checking and code quality scoring to improve AEC industry productivity. Includes MCP server for advanced a…
Falsegreen Skill
LLM skill that finds false-green tests across Python/TS/JS/Robot using the J1-J6 protocol (S-codes + the static catalog superset). Claude Code, Codex, Antigravity CLI, Cursor, CLI.
Py Lintro
Open-source AI code review engine + unified quality CLI orchestrating 15+ linters. CLI, GitHub Action, and MCP server.
Git Metrics MCP Server
MCP server for understanding team health through git metrics. A mirror for reflection, not a microscope for surveillance.
Echo Guard
Semantic linting CLI that detects codebase redundancy created by AI coding agents.
Naga
Source-as-spec architecture enforcer. Uses deep AST fingerprinting to ensure AI-generated code perfectly mirrors your internal coding standards.
Verificate MCP Quickstart
Take your vibe-coded MVP all the way to production — 17 reality gates + frontier-model review with veto power on every AI-written change. Hosted MCP; free to try, no signup.
Corralai
Corral breaks your code on purpose and checks whether your tests notice. Adversarial mutation auditing: plants goal-violating faults, runs YOUR suite against each in a sandbox, si…
Crobot
CRoBot - AI code reviews, your way. Choose your AI agent, git platform, and workflow. Open-source CLI, no per-user fees.
Mandatory Behavioral Firewall
🛡️ AI Code Quality Control System for Cursor IDE - Prevents low-quality code by enforcing mandatory research protocols before modifications. Optimized for Rust/Bevy stack with uni…
Claude Engineering Rules
Opinionated Claude Code engineering config: 11 always-on rules, 63 on-demand standards, 30 slash-command skills, 33 runtime hooks, 9 custom agents, 36 MCP servers, and a 774-item…
Massu
AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.
Skillcrossroads
Evidence-cited grades for Claude Code skills, agents, commands, MCP configs, plugins. npx skillcrossroads
Clines
Measure your codebase from the terminal — lines per language, duplicate code, complexity, token cost for AI agents, comment drift, change coupling, a refactor verdict per file, an…
Laravel Analyzer
Zero-dependency PHP static analysis CLI and MCP server for Laravel projects — security, OWASP, complexity, coupling, debt, and test coverage
Charites
Compiler-grade static analyzer & AST linter for modern web ecosystems (Astro, React/TSX, CSS)
Tectonix
Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
LintGate
Debugging is a symptom of missing infrastructure. LintGate provides the framework.
Idea Anvil
Best AI Coding Agent Pipeline Builder 2026 – Plan-Forge Drift-Proof Execution Contracts
Software Observatory
A catalog of epistemic sensors for software correctness — the observable signals that reduce uncertainty about whether a system is correct
Frappe Inspector Support
Documentation, downloads and support for Frappe Inspector
Code Clearance
Evidence-based clearance for AI-generated code.
Agent Delivery Gates
Delivery gates for AI coding agents, because green tests are not proof. Breaks your code on purpose and reports the breaks no test noticed. Runs a change's new tests against the c…
Nekoi MCP
Judges Claude Code by its own transcript, and stops the attempt at the point of intent - not after the fact. A hook and MCP server in one Go binary.
Webmcp Optimized
Refactored fork of jasonjmcghee/WebMCP, the bridge that lets a website act as an MCP server. Monolith split into focused modules, 693 to 368 line deduplication, 25 tests where ups…
Nothing New
Claude Code Skill: 五层优先级检查——先查官方，再问社区，少走弯路。太阳底下没有新鲜事。
Adversarial Review Loop
Independent second-model adversarial review gate for pushes to main (Claude authors, Codex reviews, loop until APPROVE).
Painpoints
Find the architectural pain points in any codebase. Scores every file on layering, complexity, data access, failure handling, UI cost and trust-boundary risk against Google, Amazo…
ConvergeLoop
通用型 AI 对抗性验证引擎 - 11 角色 +47 扫描器 - 修到真完美
igorolv/sonar-mcp-server
hosted SonarQube Community Build: issues, security hotspots, rules and code snippets so an agent can fix findings locally.
Euthynos
A local, read-only MCP server that gives AI coding agents structural evidence about your repository — and names the boundary of every answer.
ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架，一人全栈交付。
Debtmap
Technical-debt scanner for AI-generated and vibe-coded repos — DebtScore, git-evidence AI provenance, treemap, action plan, badge
Oversight Lint Action
GitHub Action to lint your Storybook MCP components manifest in CI, reporting findings as GitHub annotations.
Codapult Guard
Local-first architecture guardrails for JavaScript and TypeScript projects, built for AI coding agents and Next.js SaaS.
Aicaudit
aicaudit — AI-powered code audit for Python: taint-path static analysis + evidence-grounded AI verdicts. Every result ships with a machine-checkable source-to-sink path.
Code Inspection
Local multilingual code analysis and inspection for editors, terminals, and AI agents via CLI, MCP, and LSP.
Bleurs
Ground truth for AI coding agents. Blocks the APIs that don't exist, serves the ones that do — one index, both directions.
inth3shadows/runecho
the same code produces the same answer. Parsers for Go, Python, JS/TS, Rust, Ruby and shell. `bash install.sh`
Platao
Deterministic completion auditor for agent-written code: did you actually finish? Offline, zero-cost, with an MCP server.
Recurse
Recurse — independent third-party profile of a public API surface, by API Evangelist. Recurse ML is an AI-powered code review platform built for modern development workflows that…
Agent Memory Project
Coding/repo add-on overlay for the agent-memory framework — wizards, doc-gen, QA, fleet, localization, push/pull. Depends on the memory core (agent-memory-system); composes on top…
Drift
Track AI-assisted projects in your terminal with a lightweight TUI and CLI.
Andon
Andon - agent-callable code measurement. Evidence-carrying, delta-first, tamper-aware.
Lint
Static and live-protocol conformance linter for MCP servers -- audit tool schemas, docs, tests, security posture, and protocol conformance before you ship.
Juror
Cheaper and better Greptile alternative runs on your own github actions.
Sonarqube
Run SonarQube Community Build locally with Docker Compose and PostgreSQL, with persistent storage and setup instructions for connecting the SonarQube MCP server to Codex.
Agent Xray
Grade your agent's tools before the agent has to. CLI linter for MCP tool catalogs.