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.
-
—
npm MIT -
基于模板优化API查询提示的MCP服务器,提供结构化的查询建议和代码生成
npm MIT -
optimize-prompt-workflowupdated this year
A FastMCP tool for optimizing user prompts using Coze AI workflows
npm ISC -
Advanced cross-platform prompt optimization with MCP integration and 120+ optimization rules
npm Proprietary -
MCP server for optimizing and enhancing prompts for better AI interactions
npm MIT -
Advanced MCP server providing cutting-edge prompt optimization tools with research-backed strategies
MIT ★ 25 -
neko-prompt-optimizer-mcpupdated this year
MCP server for self-optimizing master prompts - Track rule usage, compress tokens, analyze dependencies
npm MIT -
ByteFun MCP服务:智能提示词优化,支持AI处理完成回调监听,提升Cursor使用体验
npm MIT -
ByteFun MCP服务:智能提示词优化,支持AI处理完成回调监听,提升Cursor使用体验
npm MIT -
MCP server for AI-powered prompt optimization - Claude Desktop, Cursor, Windsurf, and 17+ MCP clients
npm NOASSERTION ★ 1 -
simple-prompt-optimizergithub.com/Chumbayoumba/simple-prompt-optimizerupdated this year
A lightweight, robust MCP server for prompt optimization using OpenRouter and CO-STAR framework.
★ 2 -
claude-prompt-optimizer-mcpgithub.com/rishiatlan/prompt-optimizer-mcpupdated this year
The control plane for AI prompts — deterministic scoring, policy enforcement, audit & governance via MCP. Free tier included.
npm Elastic-2.0 -
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 -
Give every AI coding agent better instructions before it starts working. Local-first MCP server and portable Agent Skill.
npm MIT -
MCP server for prompt engineering: candidate prompts, LangGPT structuring, iterative optimization, promptfoo-style evals and DSPy-style train/dev search. Bring your own OpenAI-compatible key.
MIT ★ 1 -
MCP Server that offers high-performance prompt optimization server with real-time streaming, pattern-based enhancement, and comprehensive session management capabilities.
NOASSERTION ★ 17 -
MCP server for intelligent prompt optimization using meta-prompting techniques
npm MIT -
MCP server for BestMate prompt optimization - integrates with Cursor IDE
npm MIT -
prompt-packer-mcpgithub.com/amir-armaniya/prompt-packer-mcpupdated this year
AI-powered MCP server for prompt optimization. Transforms vague prompts into detailed, structured ones. Works with Claude Code, Cline, Cursor, MiMo Code, and all MCP-compatible tools.
npm MIT -
MCP Server for Promptrix - AI prompt enhancement and optimization for Claude Code
npm MIT -
A Model Context Protocol (MCP) server that provides a prompt optimization service for Large Language Models (LLMs) using Google Gemini, with advanced prompt engineering thanks to 22365_3_Prompt_Engineering_v7.pdf authored by Lee Boonstra
npm MIT -
Advanced AI prompt optimization MCP server with ML-based domain detection, templates, and analytics
npm MIT -
promptkiln-mcpgithub.com/alanshurafa/promptkiln-mcpupdated this year
Two-pass prompt optimization MCP server with local heuristic analysis and LLM-specific best practices. No API key required.
npm MIT -
MCP server integrating GEPA (Genetic-Evolutionary Prompt Architecture) for automatic prompt optimization with Claude Desktop
pypi MIT ★ 52 -
MCP server for Bench — evaluate and optimize your LLM prompts from any MCP client
npm MIT -
@abhi1381/promptpilot-mcpupdated this year
MCP server for PromptPilot — prompt optimization for Claude Code, Cursor, Codex, and more
npm MIT -
OmniEvolve: Evolutionary code & prompt optimization framework with island-model tournaments, evaluator SDK, and SQLite lineage ledger (MCP + CLI)
Apache-2.0 ★ 1 -
Agentic Work Assist - Production-ready MCP server with Constitutional AI Meta-Prompting Enhancement System featuring real-time prompt optimization, automated pattern recognition, constitutional AI-validated prompt evolution, A/B testing framework, compreh
npm MIT -
@jhaigc/prompt_flowupdated this year
MCP tool for optimizing prompts using Coze API
npm MIT -
vibe-prompt-mcpgithub.com/saurabhjambure-pixel/vibe-prompt-mcpupdated this year
MCP server that scores and optimizes vibe coding prompts
npm MIT -
Context Optimizer MCP Server v1.6.0 - Advanced MCP Server with AI External Memory Features, Persistent Storage, Differential Indexing, Content Compression, and Prompt Packaging for Master/Worker AI
npm MIT -
MCP server for intelligently formatting and optimizing prompts using rule-based analysis and structured templates
npm MIT -
prepromptgithub.com/yashdeeptehlan/prepromptupdated this year
MCP server that intercepts and optimizes prompts in Claude Code and Cursor
pypi MIT -
Autonomous Prompt Engineering, Jailbreak Defense, LLM Cost Optimizer & Eval Benchmark MCP for Cursor, Claude & Windsurf
-
ai-cost-analyzerupdated this year
MCP server that helps developers understand and reduce their AI API costs through usage analysis, savings estimation, prompt optimization, and model comparison.
npm MIT -
A Model Context Protocol (MCP) server offering professional tools and templates for hierarchical prompting, code hygiene, visualization, memory optimization, and agile planning.
npm MIT ★ 6 -
The developer toolkit for testing, analyzing, optimizing, and versioning AI prompts. (CLI, LSP, MCP Server, VS Code)
MIT ★ 1 -
PromptLab transforms basic user queries into optimized prompts for AI systems --> Built using MCP
Apache-2.0 ★ 9 -
DQLOptimizergithub.com/ancyonio/DQLOptimizerupdated this year
GitHub Copilot–native toolkit for optimizing OpenText Documentum DQL. Grounded Copilot instructions, /dql-* prompt files, specialist agents, an MCP server that supplies real generated SQL and execution plans, and a deterministic linter that fails CI on high-severity anti-patterns.
MIT -
Unified Prompt House Premium with Backend, Frontend, and MCP Server in single deployment optimized for Coolify
-
specopt-mcpgithub.com/nafwa03/specopt-mcpupdated this year
DSPy-Powered Prompt & Code Optimization via the Model Context Protocol (MCP).
MIT ★ 1 -
rtk-mcp-servergithub.com/alexiyous/rtk-mcp-serverupdated this year
Token-optimized MCP server that compresses shell tool output by 60–90%, with RTK-style prompt injection prevention for Claude Desktop
★ 1 -
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 -
@guoyuan94/dev-flow-mcpupdated this year
Token-optimized MCP Server for development workflow automation with smart prompts and resources (iOS & Android)
npm MIT -
costpilot-mcpgithub.com/solemn-cap/ai-cost-pilotupdated this year
CostPilot MCP server for per-request AI cost tracking and prompt optimization for Claude Code, Cursor, Windsurf, and more
npm MIT -
baiduan-routeractive
Route prompts across 9 LLM backends through a single MCP server — compare, optimize, and save. No lock-in, no vendor bias.
pypi Apache-2.0 -
claude-orator-mcpgithub.com/Vvkmnn/claude-orator-mcpupdated this year
🪶 An MCP server for prompt optimization in Claude Code
npm MIT ★ 2 -
geo-audit-mcpgithub.com/carter-wzq/geo-audit-mcpupdated this year
Lightweight BYOK MCP server for GEO site audits — 31 signals across 6 pillars. Returns a readiness score, pillar breakdowns, and an actionable fix prompt for AI citation optimization.
MIT ★ 1 -
Emergency_Managergithub.com/miligp/Emergency_Managerupdated this year
Intelligent multi-agent system for emergency department patient flow optimization. Combines RAG (medical protocols), MCP server, ML-based prompt injection guardrail, and real-time Streamlit dashboard with CO2 tracking. Built for Master SISE project.
-
PostgreSQL MCP Server - 63 AI-native tools for query optimization, index tuning, EXPLAIN analysis, and database health. Features pgvector semantic search, PostGIS geospatial ops, JSONB manipulation, Database Tuning Advisor, HypoPG indexes, performance monitoring, backup/recovery, and 10 prompts with 11 intelligent resources.
MIT -
FastMCP server for the Animagine XL 4.0 image generation experience, providing prompt validation, optimization, explanation, img2img, and checkpoint/LoRA management tools. Works for any Stable Diffusion XL based model.
MIT ★ 1 -
Python 3 project for the Notion MCP server, enabling advanced interactions with Claude Code. Lets users send smart to-do commands and prompts from Notion pages. Inspired by IndyDevDan’s MCP, ported to Python 3 for better performance, optimized for Linux/Debian with seamless task-coding integration.
MIT -
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.
npm MIT ★ 192 -
Mantle SQL API Model Context Protocol Server helps in connecting any MS SQL Server via `env` configuration intended to help AI models be aware of the database data context to answer LLM prompts. This MCP server provides three core tools with optimized per
npm ISC -
Deep Research Serverno update data
Perform comprehensive web research by combining AI-powered search and deep content crawling to gather extensive, up-to-date information on any topic. Aggregate and structure research data into detailed JSON outputs optimized for generating high-quality markdown documentation with LLMs. Customize documentation prompts and output paths to fit your workflow and save research results securely.
smithery -
mcp-media-toolkitgithub.com/tadeukaiba/mcp-media-toolkitupdated this year
MCP server for AI image generation and upload to S3-compatible storage. Generate images with Gemini (Nano Banana) and upload to Cloudflare R2, AWS S3, or MinIO with automatic prompt optimization. Works with Claude Code, Cursor, Codex, and any MCP client.
npm MIT -
image-mcp-generationgithub.com/aaronmeis/image-mcp-generationupdated this year
MCP Chart Agent is an AI-powered data visualization tool that generates charts from natural language descriptions. Built with React, Node.js, WebSocket, and Ollama, it uses a multi-agent system to create charts with custom backgrounds and watermarks. Features real-time streaming chat, chart export, and an experimentation for prompt optimization.
-
ArXivgithub.com/jasonleinart/arxiv-mcp-serverno update data
The ArXiv MCP Server provides a comprehensive bridge between AI assistants and arXiv's research repository through the Model Context Protocol (MCP). Features: • Search arXiv papers with advanced filtering • Download and store papers locally as markdown • Read and analyze paper content • Deep research analysis prompts • Local paper management and storage • Enhanced tool descriptions optimized for local AI models • Docker MCP Gateway compatible with detailed context Perfect for researchers, academics, and AI assistants conducting literature reviews and research analysis. **Recent Update**: Enhanced tool descriptions specifically designed to resolve local AI model confusion and improve Docker MCP Gateway compatibility.
oci -
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 -
prompt-flow-mcpupdated this year
MCP工具,用于根据用户输入调用API优化提示词
npm ISC