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.
-
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 -
@iflow-mcp/4regab-agent-rules-mcpgithub.com/4regab/agent-rules-mcpupdated this year
Model Context Protocol server that enables AI agents to fetch coding rules on-demand from GitHub repositories
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
-
MCP server that enables your agents to use coding rules from any or your GitHub repository. Instead of workspace rules files, you can now prompt agents to access the your coding rules from any repository.
MIT ★ 14 -
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 -
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 -
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.
-
Rule-based job-search toolkit: rates a posting against a typed profile, gates weak or duplicate applications, drafts documents for review. CLI, MCP server and Claude Code skills.
MIT ★ 2 -
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 -
Read-only linter for CLAUDE.md, AGENTS.md, SKILL.md and agent rules files: vendor limits, tokens loaded per session, hidden instructions and invisible characters, and files Claude Code or Codex never read. Claude Code plugin, MCP server, CLI, GitHub Action and pre-commit hook. No network. MIT.
npm MIT -
Infers architecture rules from your TypeScript repo's real import graph, gates each on statistical evidence, and emits them into the tools you already use (ESLint, dependency-cruiser, ts-arch). Turns the boundaries your code already follows into enforcement, so architecture drift gets caught, not just documented.
npm MIT ★ 8 -
Security rules for AI coding agents: 681 rules, 21 platforms, MCP server, Claude Code plugin. Web, mobile, databases, cloud, AI, banking.
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 -
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 -
Tell your coding agent a rule once: ljos remembers it, brings it back when it matters, and stops the shell commands you ruled out. Local, shared by Claude Code, Codex, Cursor and Gemini CLI.
MIT -
Shared project rules and memory for AI coding agents. Decisions, rules and failed approaches in one JEVMEM.md in your repo, read by Claude Code, Cursor and Codex, with a guard that checks Claude's commands before they run.
npm MIT ★ 150 -
Project rules for AI coding agents. An MCP server gives Claude Code, Codex CLI and Antigravity the rules for the files they are about to edit; AST checks run in a git pre-commit hook and in CI (aegis check). Zero dependencies, Python 3.9+, Apache-2.0.
Apache-2.0 ★ 4 -
whats-allowed-mcpgithub.com/stcmain/whats-allowed-mcpupdated this year
MCP server that shows what your coding agent can do without asking you: every settings file that contributes permission rules, which one wins, what runs unattended, and the rules Claude Code accepts and then ignores.
npm MIT -
Free, local memory and rules hub for AI coding tools: persistent memory for Claude Code, Codex, Cursor and Gemini CLI. One SQLite store over MCP, REST and CLI. Rules sync to CLAUDE.md and AGENTS.md. claude-mem alternative.
npm Apache-2.0 ★ 10 -
What your coding agent can do without asking you: merged permission rules, which settings file wins, and the rules your client accepts and then ignores. Free, MIT.
MIT ★ 1 -
File-bound rules for coding agents. Pin a constraint to the paths it is about; it lives in git, survives session end and tool switches, and re-checks itself. Measured: agents followed pinned rules 18/20 times versus 0/20 without.
npm MIT -
Aletheia: a free, local memory and rules hub for AI coding tools such as Claude Code, Codex, Cursor and Gemini CLI. One store any tool reads over MCP, REST or CLI; rules synced to CLAUDE.md, AGENTS.md, Cursor and more; export and import to move between to
npm Apache-2.0 -
Governance layer for AI coding agents (Claude Code, Codex): Git pre-commit + deny rules protect one person's rules and tools, a PreToolUse hook stops outbound commands, and a read-only MCP search server feeds the agent their notes. Recall@10 0.98 on a public 50-case gold set; 153 tests.
NOASSERTION -
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 -
A judge for code written by AI: plain Python, rules against hallucinations.
pypi MIT -
What's Allowedno update data
What your coding agent can do without asking you. Reads every settings file that contributes permission rules — managed policy, project, local, user — and reports the merged picture: which file each rule came from, which defaultMode wins, what proceeds unattended, and which rules the client accepts and then ignores (path rules on Write/Glob, unanchored allow globs, /path rules in user settings that anchor at the config directory, allow rules a deny rule reaches first). Four read-only tools: whats_allowed (full summary), permission_sources, rule_findings, unattended_surface. Read-only by construction — no child processes, no network, no writes; values of env entries are never read, only their names. MIT licensed. Free and MIT, with no telemetry and nothing held back. Built by Shift The Culture, who also publish paid kits for the failure modes this server surfaces: https://shifttheculture.media/agent-tools
smithery -
✅MCP server with code review rules and reproducible checks for AI coding assistants. No API key needed.
pypi Apache-2.0 ★ 1 -
AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.
NOASSERTION ★ 2 -
Project-scoped rule memory for coding agents.
MIT ★ 2 -
Koruvai for Claude Code: share skills, rules, MCP servers and notes with every teammate's agent
MIT -
Debuggatha: repo-aware code reviewer for AI coding agents. MCP server, CLI and VS Code extension with rule-traced findings.
MIT ★ 1 -
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 -
Cursor integration for Signetry: MCP server + project rule to govern coding-agent changes. Split from signetry-plugins.
Apache-2.0 -
Makes Claude and ChatGPT write like a person instead of an AI. Writing rule, checker, MCP server, Claude Code hook.
MIT -
@thewillmoss/anchor-mcpgithub.com/thewillmoss/anchor-mcpupdated this year
Portable agent working state MCP server — tasks, plans, notepads, memory, and rules for any AI coding agent
npm MIT -
Claude Code plugin for Ha Tang (hatang.dev): a skill with the integration rules and the @hatang/mcp server
MIT -
@rulecatch/ai-poolergithub.com/thedecipherist/rulecatch-sdkupdated this year
Monitor and track AI coding activity in Claude Code — real-time analytics, token usage, cost tracking, rule enforcement. Zero overhead.
npm MIT -
agent-skill-scan-mcpgithub.com/rexcoleman/agent-skill-scan-mcpupdated this year
MCP server: Scan OpenClaw SKILL.md and MCP tool definitions for security vulnerabilities. 22 rules. For Claude Code.
MIT -
Give any AI agent a way to hand humans a typeset document link (Claude Code skill, Cursor rule, MCP server)
MIT -
AI code governance for autonomous agents. Enforce architecture and business rules with AST intelligence, 54 MCP tools, and cryptographic audit trails.
npm Apache-2.0 ★ 4 -
rulecatch-sdkgithub.com/TheDecipherist/rulecatch-sdkupdated this year
Official SDK for Rulecatch — AI coding analytics, monitoring, and rule enforcement for Claude Code, Cursor, and AI coding assistants
MIT ★ 3 -
Scan and fix vulnerabilities in Python, JavaScript, TypeScript, Go, and Java code using AI-powered analysis with 200 built-in security rules.
MIT ★ 2 -
Organize Chrome bookmarks with a coding agent: a Chrome extension and a local MCP server, plus a skill that holds the naming and folder rules.
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 -
cleaner-codegithub.com/goldmembrane/cleaner-codeupdated this year
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rules file backdoors, and dependency attacks in AI-generated code. Static analysis + CodeBERT deep learning. Runs locally.
npm MIT ★ 1 -
MCP security scanner — source code audit with 25+ Semgrep rules, config health checks, SARIF output for CI/CD
pypi MIT -
AI coding harness to plan, track and search decisions. Skills, rules, CLI and MCP that mandate a structured workflow for Claude Code and Codex.
MIT ★ 2 -
bouncer — static compliance-controls checker (UK Online Safety Act & ICO Children's Code) as deterministic rule packs. CLI + MCP. No LLM.
npm MIT ★ 1 -
@ambih/coding-agent-memoryactive
Memory for AI coding agents: the plans, tasks, decisions, rules and bugs your agents work through, recorded automatically, shared with your team, readable by every agent through MCP, with a dashboard.
npm Apache-2.0 -
@mcpware/claude-code-organizergithub.com/mcpware/claude-code-organizerupdated this year
Organize all your Claude Code memories, skills, MCP servers, commands, agents, rules, and hooks — see what loads globally vs per-project, then move items between scopes
npm MIT -
A local harness for Claude Code and Codex: budgeted test runs with a stop rule, a guard for the tests you already have, and a token tree for every subagent.
MIT -
Project rules for AI coding agents (Claude Code, Codex CLI, Antigravity): MCP server, AGENTS.md bootstrap, AST checks, pre-commit hook and CI gate
pypi Apache-2.0 -
Local-first MCP memory governance for coding agents — Codex, Claude Code, Cursor, Grok, and Trae. Shared rules, deduplication, token insights, audit, and rollback.
MIT ★ 4 -
The website QA tool for your coding agent. 310+ audit rules across SEO, performance, security, accessibility and agent experience.
npm MIT ★ 312 -
Gives AI coding agents the why behind your code, and makes them keep it: file cards, rules and decisions kept in git and delivered before every edit, for Claude Code and Codex
npm MIT -
Long-term memory for Claude Code, Codex and other MCP agents: your preferences, rules and context, shared across agents and machines. Self-hosted.
Apache-2.0 ★ 1 -
claude-guardgithub.com/seongchankim1/claude-guardupdated this year
MCP server that audits AI-generated code with real-attacker techniques, then fixes only what you check. 155 rules, 5 AST auto-fixes, SARIF export.
MIT -
Real, deterministic MCP server for PC no-boot/no-display troubleshooting -- real beep-code tables and a rule-based diagnostic sequence, no LLM guessing at hardware causes.
pypi MIT -
Athenodeno update data
Spec-driven development for AI coding agents: specs, skills, agents, rules and MCP servers.
smithery -
waf_mcpgithub.com/KratosUAE/waf_mcpupdated this year
MCP server for ModSecurity WAF — monitor events, analyze attacks, tune rules & whitelist IPs via AI assistants (Claude Code, Cursor, etc.)
MIT