{
  "markdown": "# BetterPrompt MCP Server\n\n<p align=\"center\">\n  <img src=\"assets/logo.png\" alt=\"BetterPrompt MCP Logo\" width=\"200\">\n</p>\n\n[![CI/CD Pipeline](https://github.com/AungMyoKyaw/betterprompt-mcp/actions/workflows/ci.yml/badge.svg?style=flat-square)](https://github.com/AungMyoKyaw/betterprompt-mcp/actions/workflows/ci.yml)\n[![npm version](https://img.shields.io/npm/v/betterprompt-mcp?style=flat-square)](https://www.npmjs.com/package/betterprompt-mcp)\n[![MCP Compatible](https://img.shields.io/badge/MCP-Compatible-brightgreen?style=flat-square)](https://modelcontextprotocol.io/)\n[![Node.js Version](https://img.shields.io/badge/node-%3E%3D18-brightgreen?style=flat-square)](https://nodejs.org/)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.7+-blue?style=flat-square)](https://www.typescriptlang.org/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow?style=flat-square)](https://opensource.org/licenses/MIT)\n\n---\n\n## Table of Contents\n\n- [Overview](#overview)\n- [Quickstart](#quickstart)\n- [Installation](#installation)\n- [Tool](#tool)\n- [Usage Example](#usage-example)\n- [Client Integration](#client-integration)\n- [How It Works](#how-it-works)\n- [Development](#development)\n- [License](#license)\n- [Support](#support)\n\n---\n\n## Overview\n\nBetterPrompt MCP is a Model Context Protocol (MCP) server that enhances user requests using advanced prompt engineering techniques. It exposes a single, powerful tool that transforms simple requests into structured, context-rich instructions tailored for optimal AI model performance.\n\nInstead of manually crafting detailed prompts, BetterPrompt MCP converts your requests into expertly engineered prompts that get better results from AI models.\n\n**Before & After Example**\n\nWithout BetterPrompt:\n\n> \"Write a function to calculate fibonacci numbers\"\n\nWith BetterPrompt Enhancement:\n\n> \"You are a world-class AI assistant with expertise in advanced prompt engineering techniques from top AI research labs like Anthropic, OpenAI, and Google DeepMind.\n\nYour task is to provide an exceptional response to the following user request:\n\n\"Write a function to calculate fibonacci numbers\"\n\nPlease enhance your response by:\n\n1. Analyzing the intent and requirements behind this request\n2. Applying appropriate prompt engineering techniques to ensure maximum effectiveness\n3. Adding clarity, specificity, and structure to your approach\n4. Including relevant context and constraints for comprehensive understanding\n5. Ensuring optimal interaction patterns for complex reasoning tasks\n6. Specifying the most appropriate output format for the task\n7. Defining clear success criteria for high-quality results\n\nStructure your response with clear headings, detailed explanations, and examples where appropriate. Ensure your answer is comprehensive, actionable, and directly addresses all aspects of the request.\"\n\n---\n\n## Quickstart\n\nInstall and run via npx:\n\n```bash\nnpx -y betterprompt-mcp\n```\n\nOr add to your MCP client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"betterprompt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"betterprompt-mcp\"]\n    }\n  }\n}\n```\n\n---\n\n## Installation\n\nMost MCP clients work with this standard config:\n\n```json\n{\n  \"mcpServers\": {\n    \"betterprompt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"betterprompt-mcp\"]\n    }\n  }\n}\n```\n\nPick your client below. Where available, click the install button; otherwise follow the manual steps.\n\n<details>\n<summary><b>VS Code</b></summary>\n\nClick a button to install:\n\n[<img src=\"https://img.shields.io/badge/VS_Code-VS_Code?style=flat-square&label=Install%20Server&color=0098FF\" alt=\"Install in VS Code\">](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522betterprompt%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522betterprompt-mcp%2522%255D%257D)\n[<img alt=\"Install in VS Code Insiders\" src=\"https://img.shields.io/badge/VS_Code_Insiders-VS_Code_Insiders?style=flat-square&label=Install%20Server&color=24bfa5\">](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522betterprompt%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522betterprompt-mcp%2522%255D%257D)\n\nFallback (CLI):\n\n```bash\ncode --add-mcp '{\"name\":\"betterprompt\",\"command\":\"npx\",\"args\":[\"-y\",\"betterprompt-mcp\"]}'\n```\n\n[Docs: Add an MCP server](https://code.visualstudio.com/docs/copilot/chat/mcp-servers#_add-an-mcp-server)\n\n</details>\n\n<details>\n<summary><b>Cursor</b></summary>\n\nClick to install:\n\n[<img src=\"https://cursor.com/deeplink/mcp-install-dark.svg\" alt=\"Install in Cursor\">](https://cursor.com/en/install-mcp?name=BetterPrompt&config=eyJjb21tYW5kIjoibnB4IC15IGJldHRlcnByb21wdC1tY3AifQ%3D%3D)\n\nOr add manually: Settings → MCP → Add new MCP Server → Type: command, Command: `npx -y betterprompt-mcp`.\n\n</details>\n\n<details>\n<summary><b>LM Studio</b></summary>\n\nClick to install:\n\n[![Add MCP Server betterprompt to LM Studio](https://files.lmstudio.ai/deeplink/mcp-install-light.svg)](https://lmstudio.ai/install-mcp?name=betterprompt&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImJldHRlcnByb21wdC1tY3AiXX0%3D)\n\nOr manually: Program → Install → Edit `mcp.json`, add the standard config above.\n\n</details>\n\n<details>\n<summary><b>Continue</b></summary>\n\nInstall button: TODO – no public deeplink available yet.\n\nManual setup:\n\n1. Open Continue Settings → open JSON configuration\n2. Add `mcpServers` entry:\n\n```json\n{\n  \"mcpServers\": {\n    \"betterprompt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"betterprompt-mcp\"]\n    }\n  }\n}\n```\n\nRestart Continue if needed.\n\n</details>\n\n<details>\n<summary><b>Goose</b></summary>\n\nClick to install:\n\n[![Install in Goose](https://block.github.io/goose/img/extension-install-dark.svg)](https://block.github.io/goose/extension?cmd=npx&arg=-y&arg=betterprompt-mcp&id=betterprompt&name=BetterPrompt&description=Enhance%20prompts%20with%20advanced%20techniques%20for%20MCP%20clients)\n\nOr manually: Advanced settings → Extensions → Add custom extension → Type: STDIO → Command: `npx -y betterprompt-mcp`.\n\n</details>\n\n<details>\n<summary><b>Claude Code (CLI)</b></summary>\n\nInstall via CLI:\n\n```bash\nclaude mcp add betterprompt npx -y betterprompt-mcp\n```\n\n</details>\n\n<details>\n<summary><b>Claude Desktop</b></summary>\n\nAdd to `claude_desktop_config.json` using the standard config above, then restart Claude Desktop. See the MCP quickstart:\n\n[Model Context Protocol – Quickstart](https://modelcontextprotocol.io/quickstart/user)\n\n</details>\n\n<details>\n<summary><b>Windsurf</b></summary>\n\nFollow the Windsurf MCP documentation and use the standard config above.\n\n[Docs: Windsurf MCP](https://docs.windsurf.com/windsurf/cascade/mcp)\n\n</details>\n\n<details>\n<summary><b>Gemini CLI</b></summary>\n\nFollow the Gemini CLI MCP server guide; use the standard config above.\n\n[Docs: Configure MCP server in Gemini CLI](https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/mcp-server.md#configure-the-mcp-server-in-settingsjson)\n\n</details>\n\n<details>\n<summary><b>Qodo Gen</b></summary>\n\nOpen Qodo Gen chat panel → Connect more tools → + Add new MCP → Paste the standard config above → Save.\n\n[Qodo Gen documentation](https://docs.qodo.ai/qodo-documentation/qodo-gen)\n\n</details>\n\n<details>\n<summary><b>opencode</b></summary>\n\nCreate or edit `~/.config/opencode/opencode.json`:\n\n```json\n{\n  \"$schema\": \"https://opencode.ai/config.json\",\n  \"mcp\": {\n    \"betterprompt\": {\n      \"type\": \"local\",\n      \"command\": [\"npx\", \"-y\", \"betterprompt-mcp\"],\n      \"enabled\": true\n    }\n  }\n}\n```\n\n[opencode MCP documentation](https://opencode.ai/docs/mcp-servers/)\n\n</details>\n\n---\n\n## Tool\n\n### `enhance-request`\n\nTransforms user requests into world-class AI-enhanced prompts using advanced prompt engineering techniques.\n\n**Input:**\n\n- `request` (string, required): The user request to transform into an enhanced AI prompt\n\n**Output:** AI-enhanced prompt with structure, context, and clear instructions.\n\n**Example Usage:**\n\n```json\n{\n  \"name\": \"enhance-request\",\n  \"arguments\": {\n    \"request\": \"Write a function to calculate fibonacci numbers\"\n  }\n}\n```\n\n---\n\n## Usage Example\n\n**Request:**\n\n```json\n{\n  \"name\": \"enhance-request\",\n  \"arguments\": {\n    \"request\": \"Explain quantum computing\"\n  }\n}\n```\n\n**Enhanced Result:**\n\n> \"You are a world-class AI assistant with expertise in advanced prompt engineering techniques from top AI research labs like Anthropic, OpenAI, and Google DeepMind.\n\nYour task is to provide an exceptional response to the following user request:\n\n\"Explain quantum computing\"\n\nPlease enhance your response by:\n\n1. Analyzing the intent and requirements behind this request\n2. Applying appropriate prompt engineering techniques to ensure maximum effectiveness\n3. Adding clarity, specificity, and structure to your approach\n4. Including relevant context and constraints for comprehensive understanding\n5. Ensuring optimal interaction patterns for complex reasoning tasks\n6. Specifying the most appropriate output format for the task\n7. Defining clear success criteria for high-quality results\n\nStructure your response with clear headings, detailed explanations, and examples where appropriate. Ensure your answer is comprehensive, actionable, and directly addresses all aspects of the request.\"\n\n---\n\n## How It Works\n\nBetterPrompt MCP leverages the [MCP Sampling API](https://modelcontextprotocol.io/specification/2025-06-18/client/sampling) to enhance user requests:\n\n1. When you call the `enhance-request` tool, the server sends a sampling request to your MCP client\n2. Your client uses its configured LLM to enhance the prompt using advanced prompt engineering techniques\n3. The enhanced prompt is returned to you for use with any AI model\n\nThis approach has several benefits:\n\n- No API keys required - uses your client's existing LLM configuration\n- Leverages the most capable model available in your client\n- Works with any MCP-compatible client (Claude Desktop, VS Code, Cursor, etc.)\n- Always up-to-date with the latest prompt engineering techniques\n\n---\n\n## Development\n\n### Project Structure\n\n```\nbetterprompt-mcp/\n├── src/\n│   └── index.ts          # Main server implementation\n├── tests/                # Test files and verification scripts\n├── dist/                 # Compiled output (generated)\n├── package.json          # Dependencies and scripts\n├── tsconfig.json         # TypeScript configuration\n└── README.md             # Documentation\n```\n\n### Build & Development\n\nBuild:\n\n```bash\nnpm run build\n```\n\nWatch (dev):\n\n```bash\nnpm run watch\n```\n\nFormat:\n\n```bash\nnpm run format\nnpm run format:check\n```\n\nTest:\n\n```bash\nnpm run test:comprehensive\n```\n\n### Linting and Formatting\n\nWe use ESLint + Prettier to keep the codebase consistent.\n\n- Run the linter locally: `npm run lint`\n- Apply autofixes: `npm run lint -- --fix` or `npm run lint:fix`\n- Run the CI-oriented lint (JSON output): `npm run lint:ci` (produces `artifacts/lint-report.json`)\n- Autofix auto-commit policy: safe, formatting-only autofixes are auto-committed using `scripts/lint-autofix-and-commit.sh`. The script uses a conservative heuristic (small change threshold) and will abort auto-commit when changes appear large or potentially behavior-affecting; in such cases open a PR for human review.\n\n## License\n\nMIT License\n\n---\n\n## Support\n\nFor questions or issues, open an issue on [GitHub](https://github.com/AungMyoKyaw/betterprompt-mcp/issues) or contact the author via GitHub profile.\n\n---\n\n## Author\n\nAung Myo Kyaw ([GitHub](https://github.com/AungMyoKyaw))\n",
  "bytes": 11588,
  "sha": "d57a385738903188f14f0cf73aaabaf7ac93c327034e3c9fa8400b0d3bdb9eef",
  "repo_slug": "aungmyokyaw/betterprompt-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_aungmyokyaw_betterprompt_mcp_bee74cf2/readme"
}