# Mcp Gemini Prompt Enhancer

> 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

- **Type:** MCP server
- **Install:** `agentstack add mcp-andrea9293-mcp-gemini-prompt-enhancer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [andrea9293](https://agentstack.voostack.com/s/andrea9293)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [andrea9293](https://github.com/andrea9293)
- **Source:** https://github.com/andrea9293/mcp-gemini-prompt-enhancer

## Install

```sh
agentstack add mcp-andrea9293-mcp-gemini-prompt-enhancer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

[](https://badge.fury.io/js/@andrea9293%2Fmcp-gemini-prompt-enhancer) 

[](https://www.paypal.com/donate/?hosted_button_id=HXATGECV8HUJN) 

[](https://buymeacoffee.com/andrea.bravaccino)

# MCP Gemini Prompt Enhancer

A Model Context Protocol (MCP) server that provides a prompt optimization service for Large Language Models (LLMs) using Google Gemini, with advanced prompt engineering support and automatic PDF asset management.

## Reference PDF
The service uses as its main asset the PDF “22365_3_Prompt_Engineering_v7”, a comprehensive guide on prompt engineering for Large Language Models (LLMs), authored by Lee Boonstra. The document (68 pages) covers techniques and best practices for crafting effective prompts, including zero-shot, one-shot, few-shot prompting, and configuration strategies to optimize interactions with models. It is designed to help developers and data scientists achieve better results with LLMs.

Direct download link: [22365_3_Prompt_Engineering_v7.pdf](https://www.innopreneur.io/wp-content/uploads/2025/04/22365_3_Prompt-Engineering_v7-1.pdf)

## Configure MCP Client
Add to your MCP client configuration (e.g., Claude Desktop):

```json
{
  "servers": {
    "mcp-gemini-prompt-enhancer": {
      "command": "npx",
      "args": [
        "-y",
        "@andrea9293/mcp-gemini-prompt-enhancer"
      ],
      "env": {
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY"
      },
      "type": "stdio"
    }
  }
}
```

## Main Features
- API to enhance textual prompts using prompt engineering techniques
- Automatic download and management of reference PDF asset
- Cross-platform compatibility (Windows, macOS, Linux)
- FastMCP server with stdio and SSE transports (sse only for development)

## Project Structure
```
├── src/
│   ├── core/
│   │   ├── services/
│   │   │   ├── prompt-enhancer-service.ts
│   │   │   ├── utils-service.ts
│   │   └── tools.ts
│   ├── server/
│   │   ├── http-server.ts
│   │   └── server.ts
│   └── index.ts
├── package.json
├── tsconfig.json
```

## How it works
- On startup, the server checks for the reference PDF in the `.mcp-enhancer-service` folder in the user's home directory. If not present, it downloads it automatically.
- Exposes the `enhance_prompt` tool via MCP, which optimizes a textual prompt using advanced techniques and the PDF content.

## Quick Start
1. Install dependencies:
   ```powershell
   npm install
   ```
2. Set the `GEMINI_API_KEY` environment variable with your Google Gemini key.
3. Start the server as remote:
   ```powershell
   npm run start:http
   ```
   or with stdio transport:
   ```powershell
   npm run start
   ```

## Available API/tools
- `enhance_prompt`: optimizes a textual prompt

## Configuration
- The `GEMINI_API_KEY` environment variable must be set to enable integration with Google Gemini.
- The reference PDF is managed automatically.

## Main Dependencies
- [fastmcp](https://www.npmjs.com/package/fastmcp)
- [@google/genai](https://www.npmjs.com/package/@google/genai)
- [zod](https://www.npmjs.com/package/zod)
- [dotenv](https://www.npmjs.com/package/dotenv)

## License

MIT - see [LICENSE](LICENSE) file

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [andrea9293](https://github.com/andrea9293)
- **Source:** [andrea9293/mcp-gemini-prompt-enhancer](https://github.com/andrea9293/mcp-gemini-prompt-enhancer)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-andrea9293-mcp-gemini-prompt-enhancer
- Seller: https://agentstack.voostack.com/s/andrea9293
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.