MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
AI-powered code auditing via MCP using local Ollama models for security, performance, and quality analysis
npm MIT -
MCP server that audits your whole stack in one question: dead code, dependencies, security, CVEs, complexity and lint for Laravel/PHP, Python, TypeScript/React and Flutter/Dart.
MIT ★ 1 -
Scan your machine for known AI-coding-assistant supply-chain backdoor indicators (Claude Code / Cursor / Windsurf extensions, MCP servers) plus risky hook/permission config patterns. Usable as a CLI or as an MCP server.
pypi MIT -
aadc-audit-mcpgithub.com/paul-psdigital/aadc-audit-mcpupdated this year
Local stdio MCP server (and CLI) that audits a software project against the UK ICO Age Appropriate Design Code (the Children's Code). Runs entirely on the user's machine; no source code leaves the device.
npm MIT -
Turn Lighthouse audits into coding-agent tasks.
npm MIT ★ 4 -
dependency-audit-mcpgithub.com/Anicodeth/dependency-audit-mcpupdated this year
MCP server: audit a project's npm dependencies against the live registry — freshness, versions-behind, deprecation, and license. Real facts for coding agents.
MIT -
Rust 代码安全审计引擎:跨文件污点追踪 + CPG 数据流分析产出可验证证据链,通过 MCP 让 LLM 基于证据完成漏洞判定。Rust code security audit engine: cross-file taint tracking and CPG data-flow analysis produce verifiable evidence chains; MCP lets LLMs make evidence-based vulnerability verdicts.
Apache-2.0 ★ 10 -
Inspectragithub.com/Fascinax/Inspectraupdated this year
Hybrid code audit system powered by deterministic MCP tools and conditional hotspot exploration. Audits 12 domains: security, tests, architecture, conventions, performance, documentation, tech-debt, accessibility, API design, observability, i18n, and UX consistency.
npm MIT ★ 1 -
Audit AI coding agent sessions from Claude Code, Cursor, and Codex against each user's role. Flags off-role work with line-level citations. No LLM calls.
MIT -
Self-hosted MCP server for live documentation, code audits, and best practices. 795+ curated libraries, 107 audit patterns, no rate limits.
npm NOASSERTION ★ 7 -
Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.
cargo MIT ★ 24 -
mcp-siber-security-auditstale
MCP server for security code audit with auto-fix capabilities
npm MIT -
o-coding-navigationgithub.com/uncletim-gz/o-codingnavigationupdated this year
Local-first AI coding navigation CLI and MCP server with step gates, audit trail, and SOP-aware project state.
npm Apache-2.0 -
Enterprise code governance and AI audit platform. Detects AI drift, enforces organizational standards, and audits AI-generated code with continuous monitoring.
npm MIT -
Lapisan standar untuk kode buatan AI: audit, port & proyek, server MCP untuk agent coding. Lokal-dulu, open-core.
Apache-2.0 -
vigilogithub.com/Idan3011/vigiloupdated this year
Audit trail and cost tracker for AI coding agents. See exactly what Claude Code and Cursor read, wrote, and executed - locally, in real time.
MIT ★ 4 -
x402-scan-auditactive
Code audit MCP. Activate: npx x402-scan-audit --x402 https://scan-api-production-e73f.up.railway.app
npm MIT -
@tng-sh/mcp-servergithub.com/tng-sh/mcp-serverupdated this year
MCP server for TNG test generation and code auditing
npm MIT -
proofflow-mcpgithub.com/hyperion-gpu/proofflow-v0.1updated this year
MCP server for ProofFlow – audit infrastructure for AI coding agents
pypi MIT -
Claude Code plugin for site audits you can re-run and trust: scripted SEO, Core Web Vitals, links, signs of a hacked site, images and video, with evidence for every finding, repeatable scores, a client-ready report and fixes verified by a second audit.
MIT -
MCP server for smart contract audit, code security scan, and wallet risk profiling via x402. By Crest Deployment Systems.
npm MIT -
Toolkit and MCP server for auditing AI coding assistant productivity in engineering sprints
MIT ★ 1 -
Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.
pypi MIT ★ 285 -
@vibeaudit/mcpupdated this year
VibeAudit MCP Server — Run production-readiness audits from Claude Code, Cursor, and Windsurf
npm MIT -
Official AISEOgic MCP connector: run SEO, AI SEO, GEO & AEO website audits and get fix code from Claude, ChatGPT and other AI apps. Docs and config only.
MIT -
MetaLens open-source Metabase audit kit: duplicates, dead dashboards, broken questions, health score. Runs on your machine, nothing leaves it. CLI, MCP server, Claude Code skills.
MIT -
MCP server and Claude Code PostToolUse hook collector that records AI coding agent actions as tamper-evident audit evidence in EvidentTrail.
MIT -
Tamper-evident audit log and approval gate for AI coding agents (Claude Code, Cursor, any MCP client). Name reservation — first working release coming soon.
cargo Apache-2.0 -
Audit Rust projects for unsafe, FFI, and supply-chain risk — a local, read-only MCP server for your coding agent.
go Apache-2.0 ★ 1 -
mcpgithub.com/vetkit/mcpactive
vetkit MCP server: run code audits and read findings from any MCP client (Cursor, VS Code, Codex, Claude).
npm MIT -
Self-hosted source code security audits with Pi, Claude Code, local Skills and MCP. Inspect evidence, track findings, and export reports.
AGPL-3.0 ★ 1 -
Konsulto MCP server — drive the Konsulto cybersecurity audit platform from MCP-capable clients (Claude Code, etc.)
npm MIT -
Audit how well AI agents can use a web page or site, from the command line, in CI, or as an MCP server for coding agents.
npm SEE LICENSE IN LICENSE -
codeauditgithub.com/priyanshuchawda/codeauditupdated this year
Read-only MCP server for AI coding agents: repo inspection, skill routing, code audits, docs evidence checks, and issue/PR planning.
npm MIT ★ 1 -
🔧 MCP tools for coding agents: include 40+ tools (file editing, search files and async shell,...) - with a SQLite audit trail.
npm AGPL-3.0 ★ 1 -
Governed AI coding on Claude Code: tiered pipelines, audit skills, MCP server. Claude generates, your or your team decides.
npm MIT ★ 4 -
Local-first, auditable multi-agent control room for coding, review, evidence, and private remote work.
Apache-2.0 ★ 239 -
Evidence-driven engineering control plane for AI coding agents. Full Codex workflows, Claude Code MCP preview, bounded goal loops, signed evidence, audits, and fail-closed release gates.
MIT ★ 1 -
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.
MIT -
simply-ops-guardgithub.com/nardovibecoding/simply-ops-guardupdated this year
Claude Code plugin - 49 hooks + 28 MCP tools for enforcement, security scanning, prompt injection defense, VPS ops, audit logging
AGPL-3.0 ★ 1 -
Coding power tools for AI agents. 18 deterministic MCP tools: code-graph search, SAST, blast radius, wire-level PII redaction, signed audit chain. Works with Claude Code, Codex, Gemini, Cursor.
npm ★ 1 -
An MCP server that audits other MCP servers as software artifacts: registry listings, packages, configs, and tool definitions. Static checks only. It never runs the code it inspects.
pypi MIT -
Deterministic 6-phase security audit CLI, MCP server, and VS Code extension (1:1:1 parity, *os.Root confinement, SARIF 2.1.0, GHSA advisories)
MIT -
mcp-codedocgithub.com/Akshay1018/mcp-codedocupdated this year
Professional AI-driven code documentation & quality audit agent. Scans projects, identifies bugs, and persists reports locally via MCP.
MIT -
govforgegithub.com/ericvaillancourt/govforgeupdated this year
Local-first governance for AI coding agents — MCP server, CLI, audit trail, policies. Apache 2.0.
npm Apache-2.0 ★ 2 -
guardianshieldgithub.com/sparkvibe-io/guardianshieldupdated this year
Universal AI security layer - MCP server for code scanning, PII detection, prompt injection defense, secret detection, and audit logging
pypi Apache-2.0 -
MCP security scanner — source code audit with 25+ Semgrep rules, config health checks, SARIF output for CI/CD
pypi MIT -
sonic-boomgithub.com/FDiskas/sonic-boomupdated this year
🔍 Sonic-Boom: A CLI and MCP server that visualizes project logic, architectural debt, and code anomalies as frequency patterns. Surgical code auditing via the "Sonic Code" paradigm.
npm NOASSERTION ★ 1 -
Governance-first repository audit agent: four review lenses, an adversarial verifier, versioned rubric, SARIF output, MCP server and a drop-in GitHub Action. Python CLI and Claude Code skill.
MIT -
cran-mcpgithub.com/harman206/rasbupdated this year
Model Context Protocol server for Cran — drive LLM audits from Claude Code, Cursor, Windsurf, and any MCP-aware AI client.
npm MIT -
@felipesauer/mnemagithub.com/felipesauer/mnemaupdated this year
A tamper-evident, local-first audit trail for AI-agent work — an MCP server giving Claude Code, Cursor and other agents typed tools behind workflow gates, with every action recorded in a SHA-256 hash-chained log.
npm MIT -
MCP server for Proof: an audit trail for AI-written code. Records what the agent changed, what a person actually reviewed, and who signed off. Works inside Claude Code, Claude Desktop and Cursor.
npm AGPL-3.0 -
sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nodes); after departure, audit every change against them. 28 codified audit rules, tamper-evident chain, snapshots, and an MCP toolset (104 tools, 12 plugins). Everything can be FDEing.
npm MIT ★ 56 -
Human approval for exact AI agent actions: Claude Code hook, MCP server, phone approval over Telegram, tamper-evident audit log.
MIT -
quorumgithub.com/berrzebb/quorumupdated this year
Cross-model audit gate with autonomous quality loop — AST hybrid scanning, fitness gate, blast radius, structured orchestration. 19 MCP tools, 743 tests. CLI + Claude Code plugin.
npm MIT ★ 10 -
Temporary, read-only, audited database access for AI coding agents. A human opens a lease; Claude Code (or any MCP client) gets SELECT-only tools until it expires.
npm MIT -
The website QA tool for your coding agent. 310+ audit rules across SEO, performance, security, accessibility and agent experience.
npm MIT ★ 313 -
vision-audit-agentgithub.com/rogermsc/vision-audit-agentupdated this year
Turns photo and video from physical operations into structured, evidence-backed audit reports. Vision + agent engineering with a golden dataset, a CI regression gate, a coded failure taxonomy, and MCP exposure.
Apache-2.0 -
codegraph-mcpgithub.com/cognis-digital/codegraph-mcpupdated this year
No-train, on-prem code knowledge graph served to AI agents over MCP, with a hash-chained audit row for every read.
NOASSERTION ★ 7 -
@ccwdesign/seo-skillgithub.com/ccwdesign/seo-mcp-serverupdated this year
SEO tools for AI coding assistants — audit pages, generate meta tags, and fix SEO issues from Cursor, Claude, Windsurf, and VS Code.
npm MIT