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. 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.
-
Conventional Commits and Conventional Branch enforcement, validation, and generation
MIT -
Conventional Commits and Conventional Branch enforcement, validation, and generation
pypi MIT -
artistally-mcpgithub.com/Alchemy-Lab-Infra/artistally-mcpupdated this year
Free fan-convention data for AI agents: dates, registration windows & table costs, US & Canada
MIT -
MCP server that learns coding conventions from PR review comments and enforces them
npm MIT -
iflow-mcp_enhanced-mcp-memorygithub.com/cbunting99/enhanced-mcp-memoryupdated this year
Enterprise-grade MCP server with sequential thinking, project convention learning, and intelligent memory management
pypi MIT -
Smart Git Model Context Protocol (MCP) server & CLI for conventional commits, pre-PR security secret audits, and merge conflict resolution.
MIT -
Reads the conventions your repository already keeps, with a count behind every claim. Never blocks.
MIT -
sensegithub.com/luuuc/senseactive
MCP server for AI coding agents - gives Claude Code, OpenCode, Cursor, and Codex CLI structural understanding of your codebase: symbol graph, blast radius, semantic search, conventions.
MIT ★ 47 -
chameleongithub.com/crisnahine/chameleonupdated this year
Auto-derives codebase conventions from repo analysis and injects archetype-aware guidance into AI-generated code, enforcing team idioms, banned imports, and framework-specific patterns for TypeScript/JavaScript, Ruby, and Python projects.
MIT ★ 8 -
Generate conventional commit messages from your staged git changes using Model Context Protocol (MCP)
MIT ★ 9 -
gitstorygithub.com/cognis-digital/gitstoryupdated this year
Changelog and release notes from conventional commits
NOASSERTION -
Agentic workflow replay & audit with OTel GenAI semantic conventions
NOASSERTION -
oak-cigithub.com/goondocks-co/open-agent-kitupdated this year
CLI toolkit for AI-powered development workflows - spec-driven development, RFC/ARC management, and shared conventions across AI coding agents
pypi MIT -
japan-ux-mcpgithub.com/mrslbt/japan-ux-mcpupdated this year
MCP server for Japanese web UX conventions. Generates and audits forms, typography, layout, trust signals, legal requirements, keigo, and seasonal design.
MIT -
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
MIT ★ 795 -
sourcebookgithub.com/maroondlabs/sourcebookupdated this year
Generate AI context files from your codebase's actual conventions. Not what agents already know — what they keep missing.
NOASSERTION ★ 3 -
Token usage across Claude Code, OpenCode, Codex & ZCode on one yardstick — plus a project mem log and convention-debt tracker agents query via 3 MCP tools. No server, your data stays local
npm MIT -
MCP server that gives AI coding agents a project's context (overview, conventions, security rules, features) and checks their code against the team's rules.
MIT -
mcp-lint-toolsgithub.com/rog0x/mcp-lint-toolsupdated this year
MCP server for code linting: style checker, naming convention analyzer, cyclomatic complexity, dead code finder, import analyzer Install: npx @rog0x/mcp-lint-tools
NOASSERTION -
Local-first document vault manager for macOS. Names, files and tags your documents by convention — no database, no cloud, no proprietary format. Agent-legible: --json everywhere, plus an MCP server.
MIT ★ 1 -
Ghidra MCP Server — 200+ MCP tools for AI-powered reverse engineering. GUI plugin + headless server, lazy tool loading, convention enforcement, batch operations, Ghidra Server integration, and Docker deployment.
Apache-2.0 ★ 6,237 -
Token usage across Claude Code, OpenCode, Codex & ZCode on one yardstick — plus a project memory and convention-debt tracker agents can query via MCP. No server, your data stays local.
MIT ★ 1 -
japan-ux-mcpgithub.com/mrslbt/japan-ux-mcpupdated this year
Japan Design — UI + UX correctness for AI coding agents. Enforces Japanese front-end (typography, colour, layout) and UX (forms, keigo, trust) conventions on real CSS/markup, with JLReq/JIS citations.
npm MIT -
Free MCP server for Industry 4.0 / IIoT: Sparkplug B topic linter, Unified Namespace (UNS) convention checker and an industrial AI-readiness diagnostic. No API key required.
MIT -
BaZi API for Four Pillars of Destiny charts. Day Master, Ten Gods, hidden stems, Na Yin, and typed day, year and hour conventions echoed back.
MIT -
ontomicsgithub.com/EtienneChollet/ontomicsupdated this year
Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.
MIT ★ 43 -
toon-memorygithub.com/luiggival08/toon-memoryupdated this year
The Continuity Layer for AI Agents — an MCP memory server that preserves project knowledge, decisions, and conventions across sessions so every session starts where the last one ended. Offline, token-efficient, no LLM, no server; works with 20+ agents.
npm MIT -
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.
npm NOASSERTION ★ 68 -
⚓️ A shared knowledge layer for coding agents. Serves each agent only the decisions and conventions that govern the file it has open, over MCP — then records whether the code still honors them. Your source never leaves your machine.
AGPL-3.0 -
Agent memory you can code-review. Tusk indexes a folder of markdown into a typed, searchable graph your agents query over MCP. It stays plain files in git, and tusk doctor fails CI when a link dangles or a convention breaks.
Apache-2.0 ★ 4 -
autologygithub.com/Curt-Park/autologyupdated this year
A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.
MIT ★ 25 -
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving layer.
MIT ★ 27 -
codebase-contextgithub.com/patricksys/codebase-contextupdated this year
Local repository maps, code search and symbol references for coding agents. MCP server with model-free keyword search and optional embeddings.
npm Elastic-2.0 -
MCP server for Git with local Ollama — zero tokens for git operations
MIT ★ 46 -
smart-commitgithub.com/subhayu99/smart-commitupdated this year
An AI-powered git commit message generator with repository context awareness, built with Python and Typer.
MIT ★ 2 -
AI-powered git commit rewriter, PR generator, and MCP server for Jira, Confluence, and Datadog. Single Rust binary.
BSD-3-Clause ★ 2 -
leadcodegithub.com/julxoo/leadcodeupdated this year
Virtual Lead Tech MCP server for Claude Code – analyzes repos, fetches docs via Context7, and generates tailored CLAUDE.md files
npm MIT -
promptlygithub.com/MuhammadUsmanGM/promptlyupdated this year
MCP server that refines your coding prompts with real codebase context before your AI agent acts on them.
MIT ★ 3 -
MCP-powered, agentic commit workflow: AI agents (Claude Code, Cursor) and developers commit through your team rules. Checked, formatted and enforced on every commit.
npm MIT -
repo-mcpgithub.com/westkevin12/repo-mcpupdated this year
A professional-grade MCP server for cleaning Git repositories. Automate secret audits with TruffleHog, sanitize history using git-filter-repo, and intelligently squash noise commits to transform messy dev logs into clean, production-ready codebases.
GPL-3.0 ★ 2 -
MCP server for Sqemo. AI agents query and edit ERDs, generate physical names from your team's shared glossary, import/export SQL (7 dialects) and DBML, and diff the model against a live database.
MIT -
AI Governance Era v6.1: loungeservice-grade project initialization. Creates 8-folder structure with complete AI governance (AI_RULES.md, AI_ROLE_MATRIX.yaml, NAMING_EXCEPTIONS.md, DEVELOPMENT.md, project.md) and bridge files (.cursorrules, .windsurfrules)
npm MIT