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.
-
mcp-cursor-ai-rulesstale
MCP server for managing and applying cursor rules
npm MIT -
Local MCP server and CLI for learned AI guardrails, memory, skills, and agent config injection
pypi Source Available — free for personal use, commercial/government use requires wri -
Read-only local security gate & scanner for AI coding workflows, MCP, and package hallucination risks.
MIT -
@tenantegroup/ai-rules-mcpactive
Unified MCP server providing AI coding rules for Cloudflare Backend, Nuxt Frontend, Flutter Client, and dotNET MAUI stacks with smart context filtering
npm MIT -
AI规则遵守MCP工具服务器 - 64个AI工具:38个编码规范 + 7个监督指导 + 14个智能搜索 + 5个控制台调试工具
npm MIT -
Dockerised MCP server that serves a team's AI skills and rules from a Git repo to Cursor, Claude Code, Cline and Windsurf
-
Rule MCP Server for AI agents to retrieve and apply coding rules
npm MIT -
MCP server that automatically enforces rules from markdown files for AI agents
npm MIT -
@optima-quantum/claude-critical-rules-mcp-newupdated this year
MCP server providing 21 critical rules for Claude AI based on 96+ documented failure patterns
npm MIT -
Catch the moment your AI agent drifts from its rules.
npm MIT -
@optima-quantum/claude-critical-rules-mcpupdated this year
MCP server providing critical rules for Claude AI to prevent 96 documented failure patterns
npm MIT -
MCP server for Claude AI providing automatic enforcement of critical rules - Prevents 96 documented failure patterns
go MIT ★ 7 -
MCP server that provides a portable and enhanced alternative to editor-specific documentation rules (like Cursor Rules). It allows you to define project documentation and context in standard Markdown files, making them usable across any MCP-compatible AI
npm mit -
Open, sourced rule data for calls and AI voice agents: calling hours, recording consent, AI disclosure and voice agent lint rules, with citations and as-of dates. Informational, not legal advice.
MIT -
Sigma rules for ransomware, threat actors and vulnerabilities disclosed in AI/LLM apps and MCP servers, with multi-backend conversion and an MCP server for Claude Code, Codex and Cursor. CI-pinned claims.
MIT ★ 2 -
rulith-mcpactive
MCP server providing AI rules, coding standards, and skills to agents
npm MIT -
ai-rete-rag-mcpactive
MCP server for ai·rete·rag — deterministic rule-based decisions with RAG-powered explanations
pypi MIT -
@iflow-mcp/jinjos-vibe-mcpgithub.com/jinjos/vibe-mcpupdated this year
MCP server for vibe-cli - Universal AI rules system
npm MIT -
@trentapps/manager-protocolupdated this year
Enterprise Agent Supervisor - Rules Engine MCP Server for AI Agent Governance
npm MIT -
MCP server for AI knowledge repository (rules, skills, workflows, agents)
npm MIT -
Share and import AI IDE rules securely via MCP (Model Context Protocol)
npm MIT -
World Games - the rules layer for AI-driven interactive games. Deterministic rule engine, 64 MCP tools, context ledger, save library, read-only bilingual live stage. Python standard library only.
MIT ★ 20 -
World Games - the rules layer for AI-driven interactive games. Deterministic rule engine, 64 MCP tools, context ledger, save library, read-only bilingual live stage. Python standard library only.
MIT -
World Games - the rules layer for AI-driven interactive games. Deterministic rule engine, 64 MCP tools, context ledger, save library, read-only bilingual live stage. Python standard library only.
MIT ★ 1 -
lore-ossgithub.com/eliasem-ka/lore-ossupdated this year
Agent-driven, human-in-the-loop knowledge base: AI agents extract business rules from code via MCP, reviewers approve/reject in a web UI, and rejected rules feed back to refine — a converging loop.
AGPL-3.0 -
Local MCP server that audits your git changes against the repo's own AI rules (AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Kiro, skills).
npm MIT -
agentic-travel-recommendations-apigithub.com/andypnguyen11-gif/agentic-travel-recommendations-apiupdated this year
Multi-tenant service that lets an external AI concierge generate partner-rule-compliant travel recommendations from member history and loyalty tier — deterministic rule engine (category exclusions + caps), enforced tenant isolation, exposed over REST and MCP.
-
Luthor plugin for Claude: AI-assisted marketing compliance pre-review (SEC Marketing Rule, FINRA) through the Luthor MCP server.
NOASSERTION -
Dynamic coding standards, clean architecture rules, and linter policy loader for Claude Code and AI pair programmers.
-
Catch logic contradictions in AI prompts, rules, and compliance policies — deterministic truth table engine with MCP, CLI, and NL support
pypi AGPL-3.0-only -
argusgithub.com/Dragoon0x/argusupdated this year
The design intelligence runtime for AI agents. 49 rules. Zero LLM. MCP-native. Give your agent eyes.
MIT ★ 5 -
PR-Distillergithub.com/rendermani/PR-Distillerupdated this year
Extract reusable coding rules from your team's PR review history and serve them to AI coding assistants in real-time via MCP.
NOASSERTION ★ 1 -
Repo rules enforcement for AI agents. Checks diffs against AGENTS.md conventions and custom policy, and blocks violations before they land.
npm MIT -
loan-ai-assistantgithub.com/aishwarya14-dev/loan-ai-assistantupdated this year
This project extends the Loan Rule Engine with an AI Operations Assistant using MCP. It communicates with the Rule Engine over REST APIs and provides natural language access to rule evaluations, analytics, and audit information.
-
Your AI agent learned public code, not your team's PR decisions. difflore CLI serves source-backed team rules via MCP.
cargo Apache-2.0 ★ 1 -
Reusable AI agent toolkit: Agent Skills, coding rules, MCP servers, Git workflows, frontend utilities, and TinyPNG image tools. 可复用 AI Agent 技能、规则与 MCP。
MIT -
See everything that runs on a Dataverse table: plugins, workflows, cloud flows, business rules, form scripts, PCF, data rules - organized by event and pipeline stage. Exports Markdown/JSON and is invokable by AI agents through the PPTB MCP server.
npm MIT -
Prism Context Engine — Context Governance for LLMs. MCP server that gives AI coding assistants (Cursor, Claude, Windsurf, VS Code) your project's architectural rules, design system, and security constraints.
npm MIT -
self-improveupdated this year
Self-improving MCP server that learns from your corrections. Stores coding rules as searchable knowledge with vector similarity search — so AI assistants never repeat the same mistakes.
npm MIT -
AI-powered rule automation system for RooCode. Automates rule generation, enforcement, and code enhancement by connecting RooCode with an AI-driven MCP that analyzes context, applies structured rules, and improves code quality intelligently.
-
Huntable CTI Studio is an AI-assisted cyber threat intelligence workbench that turns open-source CTI into Sigma rules.
MIT ★ 12 -
AI-powered development toolkit for Unity game development in Cursor IDE. 18 skills, 8 rules, 4 MCP tools, 20 snippets, 5 templates covering the full Unity lifecycle.
NOASSERTION ★ 5 -
Free MCP server, Cursor rule and Claude skill that help AI coding assistants avoid common security holes in vibe-coded apps (Supabase RLS, leaked keys). By SealMyApp.
MIT -
@trajendran/commerce-tools-mcpgithub.com/trajendran/commerce-toolsupdated this year
MCP server and Cursor rules for Adobe Commerce development - local Commerce module development, GraphQL, REST API, and environment management with AI-powered tools
npm MIT -
Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, Claude Code & VS Code.
pypi MIT ★ 6 -
UK Company Pre-Screen: a public-record check of UK companies for commercial underwriters. Written rules set the route; AI agents explain it over MCP, inside guardrails; every check that couldn’t run is named.
MIT -
Governed AI-ops for OPNsense + pfSense firewalls — gateway/rule/traffic RCA, guarded rule/alias writes, with audit/budget/undo (preview)
pypi MIT ★ 2 -
HeartFlow (心虫) — AGI Layer 1: the Discriminator. Rule-based engine that checks what AI says before it reaches humans. 46 discrimination dimensions, 9-layer pipeline, 137 modules (logic/decision/cognition/emotion/memory/ethics/collaboration), 179 MCP tools
npm MIT -
ai-security-gatewaygithub.com/etho0/ai-security-gatewayupdated this year
Hybrid AI Security Gateway — rule-based + LLM-assisted (Nemotron + Llama) prompt injection detection + MCP security (rules+policy+AI Assisted)
MIT ★ 2 -
ibitlabs-mcpgithub.com/agentbonnybb/ibitlabsupdated this year
MCP server for iBitLabs — live receipts from a public $1k → $10k AI trading experiment. Exposes balance, contributor ledger, adopted shadow rules, and saga chapters as callable tools so any LLM agent can cite real fills instead of hypothetical backtests.
npm MIT -
snhpactive
Negotiation rules your AI can't break: turn a seller's offer into rules and draft replies to buyers (and their AI agents) inside them. MCP server for snhp.dev.
pypi Apache-2.0 -
p-layersupdated this year
Memory for AI agents with rules that are kept, not just written. P0-P6 layered rules enforced in code. SQLite + FTS5 + pluggable embeddings, PostgreSQL backend, MCP server, eval harness. (GitHub: p-layer)
pypi MIT -
Security rules for AI coding agents: 681 rules, 21 platforms, MCP server, Claude Code plugin. Web, mobile, databases, cloud, AI, banking.
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 -
Reference implementation of the context-at-source pattern: in-repo AI rule files, a rule-aggregation generation script, and a custom MCP server feeding a live API to an AI coding agent.
MIT -
Memory for AI agents with rules that are kept, not just written - P0-P6 layered rules enforced in code, SQLite + PostgreSQL, MCP server, eval harness. PyPI: p-layers
MIT ★ 3 -
agentcourt-apigithub.com/vbkotecha/agentcourt-apiupdated this year
Policy-driven dispute resolution API for AI agent commerce | 7 policies, 39 rules, <500ms rulings | x402 USDC payments on Base | MCP server, Python/JS SDKs
MIT ★ 3 -
saas-MCP-accountantgithub.com/ermiazhalehpourmianj/saas-MCP-accountantupdated this year
🐳 This project is a secure, rules-driven financial automation system designed to operate as an MCP-orchestrated accountant. Instead of relying on traditional budgeting apps or manual bookkeeping, the system applies deterministic logic, explainable rules, and AI-assisted workflows to analyze & org
MIT -
Your AI, on the canvas — connect Claude Code, Cursor, or any MCP client to Figma: read, edit, audit, build. The file itself carries your rules and rulings. Works on every Figma plan.
npm MIT ★ 4 -
Prompt-injection scanner for content AI agents read: issues, PR bodies, READMEs, comments, docs. Deterministic rules for hidden unicode, HTML comment instructions, exfil patterns, tool lures, and base64 payloads, with file, line, rule id, and severity for every finding.
npm MIT