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.
-
A comprehensive MCP server providing deep engineering guidance with full MCP compliance: tools, resources, prompts, and secure file system access
npm MIT -
LLM apps course homework: prompt engineering (LangChain), tool use (TSETMC), and a multi-tool MCP finance server — all Dockerized
MIT -
A prompt-engineering setup that makes any AI coding tool plan first, build in order, and hold an elite bar. Skills pack + hosted MCP server.
MIT -
motion-site-buildergithub.com/olbboy/motion-site-builderupdated this year
A retrieval-driven engine + 17-rule linter that plans, builds, and grades motion UI across five design languages — 92 prompts, 8 MCP tools, 3 agent skills. Motion that looks designed, not generated.
MIT ★ 4 -
Provider-neutral prompt calibration engine with sensitivity-ranked meta-axes, hard-gate x soft-score fitness, walk-forward ship gates, guarded/expedition profiles, and explicit capability/risk reporting across Anthropic, OpenAI, Gemini, and local OpenAI-compatible backends. Optional sub-tools (mini-omega-lock, mini-antemortem-cli) distribute separately and plug in via the omegaprompt.preflight interface.
pypi Apache Software License -
Official MCP Python server exposing typed data-engineering tools, resources, prompts, read-only SQL, and synthetic ETL investigations.
-
MCP server for horizOn Backend-as-a-Service: documentation, live API tools, and workflow prompts for Godot, Unity, and Unreal Engine integration.
npm MIT -
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
MIT ★ 5 -
MCP server that lets Claude and other AI apps query EvenKeel expense data through tools, resources and prompts, reusing EvenKeel's own engine.
MIT -
aidigital-labs-mcpupdated this year
MCP server for AI Digital Labs tools — website audits, neuromarketing, prompt engineering, AIO optimization, and synthetic focus groups
npm UNLICENSED -
conduitgithub.com/naumanAhmed3/conduitupdated this year
An MCP (Model Context Protocol) server exposing a pgvector hybrid-retrieval engine as tools, resources and prompts over Streamable HTTP.
-
adler-mcpgithub.com/commit3296/adlerupdated this year
Model Context Protocol server for the Adler OSINT username-search engine — exposes scan / list / doctor / history tools, registry + scan-history resources, and OSINT workflow prompts.
cargo MIT -
A Model Context Protocol server with machine learning engineering tools: BPE token counting and cost estimates, BM25 search, paired bootstrap and McNemar evaluation comparison, JSON Schema validation, and prompt-injection and PII scanning.
MIT -
Media generation, editing, and extraction as MCP tool surfaces — image, video, audio, OCR, TTS/STT. Chainable into workflows with per-step prompt engineering and quality gates. A slice of a 250+ model production roster.
go MIT -
ai-forge-mcpgithub.com/HurtzDonutStudios/ai-forge-mcpupdated this year
565 AI-callable tools across 16 MCP servers. Full-pipeline AAA game asset production. Controls Blender, Substance Suite, Maya, Houdini, and Unreal Engine 5. 50 specialized AI agents. One prompt in, game-ready asset out.
★ 102 -
元构·智能生命体(MetaGO Intelligent Lifeform)MCP Server — 55 tools (22 思维工具 + 32 核心技能 + 1 事件上报) + 8 prompts。Engine V2.1.3 硬驱动:KMWI 四层记忆 + 元进化五阶段 + 技能智能生成调用真实代码 + 927 算法驱动(via @metago-ai/algorithms)。任何 MCP 协议客户端(Claude Desktop/Cursor/Trae/ZCode 等)即开即用。基于 Model Con
npm MIT -
SEO Performanceno update data
Post-publish SEO performance MCP. Unifies **Google Search Console, Matomo, GA4, Microsoft Clarity, and AI-citation signals** per URL and emits a **verdict per post** (refresh / expand / merge / kill / double_down / hold) with deterministic reason codes and a 0-1 confidence score. Reporting only — never mutates posts. Works with any CMS via XML sitemap; optional Ghost Admin API integration for richer metadata. ## Tools - **posts.list** — discover posts via XML sitemap, JSON override, Ghost Admin API, or explicit URL list. - **posts.snapshot** — unified 30/60/90-day signal pull across every configured source for one URL. - **posts.decay_curve** — weekly GSC bucket + decay / plateau / growth classification. - **posts.verdict** — rule-based verdict engine: refresh, expand, merge, kill, double_down, hold. - **posts.refresh_brief** — markdown brief: verdict + reasons + numbers + suggested actions. - **posts.cite_loss** — list of LLMs that previously cited this URL but no longer do. - **cohort.report** — verdict engine across a cohort, ranked by verdict priority + confidence. - **gsc.quick_wins** — pages at positions 5-15 with low CTR, ranked by impressions. ## Prompts - **audit_cohort** — run cohort.report and generate refresh briefs for every actionable URL. - **find_quick_wins** — propose query-verbatim title and H1 rewrites for SERP underperformers. - **citation_loss_sweep** — find URLs that lost LLM citations and recover them. ## How it works Each source is best-effort: if its env vars are missing the field is omitted. Returns whatever is available. Optional DuckDB cache layer for historical comparisons. Platform-agnostic — works with WordPress, Hugo, Astro, Next.js, Webflow, Framer, Wix, Squarespace, Substack, Ghost, and any CMS that exposes a sitemap.
smithery -
Local-first prompt library and version-control system for AI prompts (Desktop App, CLI, MCP Server, and AI execution engine).
npm MIT ★ 11 -
WooX Prompt Tool - 智能提示词优化服务,基于MCP协议的交互式提示词分析和优化工具。支持Cursor、Augment、Claude的自动指令拦截和智能优化。
npm MIT -
A Python Module Which Compacts LLM Prompts
pypi MIT -
opencode-prompt-coachgithub.com/your-org/opencode-prompt-coachupdated this year
An MCP server that adds a /coach slash command to opencode. Evaluates and rewrites developer prompts using 8 prompt engineering frameworks.
npm MIT -
Prompts as MCP tools
MIT ★ 4 -
@jhaigc/prompt_flowupdated this year
MCP tool for optimizing prompts using Coze API
npm MIT -
Modular MCP server for programmatic prompt engineering. Provides intelligent prompt assembly for PRD generation, codebase analysis, and bug analysis with support for 31 technology stacks.
npm MIT ★ 4 -
Local prompt refinement with a Rust MCP server and optional API proxy. Development-stage tooling with documented privacy and integration boundaries.
MIT ★ 2 -
meta-prompt-mcpgithub.com/kapillamba4/meta-prompt-mcpupdated this year
MCP server providing on-demand access to official prompting guides for building robust meta-prompts.
pypi MIT ★ 3 -
MCP-first prompt governance, refinement, and engineering evidence correlation
MIT -
prompt-refinerygithub.com/farukalpay/prompt-refineryupdated this year
Retrieval-grounded prompt refinement as a Python library, CLI, and MCP server
GPL-3.0 ★ 5 -
Open-source one-key prompt enhancement engine — turn vague ideas into structured task specs anywhere you type to an AI. CLI · MCP server · playground. Zero dependencies, BYOK, offline-capable.
npm Apache-2.0 ★ 1 -
prompt-toolkit-mcpgithub.com/Money-Monkey-26/prompt-toolkit-mcpupdated this year
Production-tested AI prompt templates as an MCP server. 5 free prompts for code review, debugging, testing, and architecture.
MIT ★ 1 -
Libreria locale-first per prompt AI — vault cifrato, ricerca semantica offline, MCP-ready, AGPL 3.0
AGPL-3.0 ★ 2 -
prompt-modules-mcpgithub.com/davidlopez/prompt-modulesupdated this year
MCP server + CLI for Prompt Modules — automatic module registry that makes AI remember reusable prompt modules between sessions
npm MIT -
lazy-toolgithub.com/mcp-shark/lazy-toolupdated this year
local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools
go MIT ★ 40 -
Give every AI coding agent better instructions before it starts working. Local-first MCP server and portable Agent Skill.
npm MIT -
本地优先的提示词与 Skill 资产库:快速搜索、收藏复用、来源与有效性追踪,安全接入 Codex/MCP。 Local-first prompt & Skill library for offline search, reuse, metadata, and Codex/MCP.
★ 1 -
mcp-prompt-optimizergithub.com/yusufkucukates/mcp-prompt-optimizerupdated this year
The MCP server that turns vague AI prompts into production-ready instructions — works offline, gets smarter with an API key
MIT ★ 2 -
Read-only MCP and OpenClaw tools for video prompts and reference-aware sequences
MIT -
Structured Engineering Development MCP Server for AI coding assistants.
MIT -
Deterministic workspace mapper that assembles layered LLM context from your project's folder tree.
NOASSERTION ★ 1 -
Advanced MCP server providing cutting-edge prompt optimization tools with research-backed strategies
MIT ★ 25 -
DeepSeek Harness 的三合一能力台:提示词定制(按名称屏蔽 / 替换 / 注入 / 排序,按会话阶段与 agent 预设分层)+ 技能集合管理(导入 / 分组 / 开关)+ MCP Server 接入(分层遮蔽与工具级启停)。纯插件注入,不动官方源码。
npm MIT -
Read-only MCP tools and OpenClaw Skill for OpenSora video prompt design and shot planning.
MIT -
A comprehensive prompt management system with MCP server capabilities for seamless integration with AI tools like Cursor
MIT -
Local-first MCP server for intelligent context that feeds your prompts
pypi MIT ★ 10 -
Ask AI to build props in Blender and import them into Unity or Unreal Editor. MCP, PBR materials, stable revisions and verified scene results.
MIT ★ 2 -
promptbook-mcpgithub.com/isaacpalomero/promptbook-mcpupdated this year
Personal cookbook for AI prompts - MCP Server with RAG-powered semantic search
MIT ★ 3 -
Deterministic read-only MCP tools and OpenClaw Skill for creative motion prompts and reference-aware video sequences.
MIT -
One-key prompt enhancement — turn vague ideas into structured task specs anywhere you type to an AI. CLI + MCP server. Zero dependencies, BYOK, offline-capable (Ollama).
npm Apache-2.0 -
Read-only MCP and OpenClaw tools for bilingual China AI video prompts and reference-aware shot planning
MIT -
Read-only MCP tools and OpenClaw Skill for original Hotel Lobby-style duet prompts and shot plans.
MIT -
repoprompt-windowsgithub.com/MiaAI-Lab/repoprompt-windowsupdated this year
RepoPrompt for Windows — Context Engineering Tool for AI Coding Agents. Windows port of repoprompt/repoprompt-ce.
Apache-2.0 ★ 2 -
12 thinking prompts in English & 中文 — ask, learn, solve, decide, know yourself. Web + MCP server + AGENTS.md + Cursor rules + Claude Skill. Not tied to any one AI.
NOASSERTION ★ 3 -
compliance-watchgithub.com/robertogfortes/compliance-watchupdated this year
Contract and invoice compliance auditor built with Claude API. Hybrid RAG, tool use, MCP server, prompt evaluation, extended thinking. Full pipeline — not a chatbot.
MIT ★ 2 -
Deterministic read-only MCP tools and OpenClaw Skill for Seedance-oriented prompts and reference-aware video sequences.
MIT -
mcp-auditgithub.com/archonics/mcp-auditupdated this year
Archonics MCP server — free-tier context engineering audits for production AI agents
npm MIT ★ 1 -
prompticgithub.com/cppis/prompticupdated this year
MCP tool that analyzes your prompts — scores quality, reveals what AI inferred vs. missed, and tracks improvement over time. Works with Claude Desktop & Claude Code.
-
A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.
pypi Apache-2.0 ★ 44 -
preflight-devgithub.com/terminalgravity/preflightupdated this year
Preflight checks for AI coding agents — catch vague prompts, surface missing context, search session history
npm MIT -
MCP server for converting free-text prompts into structured thinking frameworks with validation and gap detection.
npm MIT -
Git-like versioning for prompts with eval-gated promotion. Store, diff, tag (draft/staging/production), A/B serve, and gate promotion on eval results. Self-hosted, not SaaS.
MIT