What is GemForge-mcp?

GemForge-mcp is a Model Context Protocol (MCP) server that provides specialized tools for interacting with Google’s Gemini AI models, Claude and other MCP-compatible hosts. It offers intelligent model selection, advanced file handling, and optimized prompts.

What is MCP (Model Context Protocol)?

MCP is an open protocol that standardizes how applications provide context to LLMs (Large Language Models), facilitating seamless integration and communication between different AI models and applications.

How do I install GemForge-mcp?

Clone the repository, install dependencies using npm install, and build the project with npm run build.

How do I configure GemForge-mcp?

Create a .env file in the root directory and set the GEMINI_API_KEY, DEFAULT_MODEL_ID, and GEMINI_PAID_TIER variables.

How do I run the GemForge-mcp server?

Run from source using npm run start or from compiled JavaScript using npm run start:dist.

What is Smithery.ai and how does GemForge-mcp integrate with it?

Smithery.ai is a platform for deploying AI tools. GemForge-mcp includes a smithery.yaml file for easy deployment and configuration on Smithery.ai.

How do I deploy GemForge-mcp using Docker?

Build the Docker image using docker build -t gemforge-mcp . and run the container with the required environment variables, such as GEMINI_API_KEY.

What are the available tools in GemForge-mcp?

GemForge-mcp provides four tools: gemini_search, gemini_reason, gemini_code, and gemini_fileops for various AI tasks.

What does the gemini_search tool do?

The gemini_search tool generates responses based on the latest information using Gemini models with Google Search integration.

How does the gemini_reason tool work?

The gemini_reason tool solves complex problems with step-by-step reasoning using advanced Gemini models.

What is the purpose of the gemini_code tool?

The gemini_code tool analyzes codebases using Repomix and Gemini models to answer questions about code structure, logic, and potential improvements.

What can I do with the gemini_fileops tool?

The gemini_fileops tool performs efficient operations on files (text, PDF, images, etc.) using appropriate Gemini models.

How does GemForge-mcp handle model selection?

GemForge-mcp implements intelligent model selection based on task type (search, reasoning, etc.) and available models (FAST, BALANCED, ADVANCED, LARGE_CONTEXT).

What are the special features of GemForge-mcp?

Special features include system instruction hoisting, XML content processing, file type detection, rate limiting handling, error recovery, custom Repomix options, and multi-file processing.

How do I use multi-file analysis with gemini_fileops?

Pass an array of file paths to the file_path parameter in gemini_fileops, ensuring consistent file types and providing a specific instruction parameter.

What environment variables are required for Docker deployment?

The required environment variables are GEMINI_API_KEY, GEMINI_PAID_TIER (optional), and DEFAULT_MODEL_ID (optional).

How can I contribute to GemForge-mcp?

Fork the repository, create a feature branch, commit your changes, push to the branch, and open a Pull Request.

Where can I find the license information?

The project is licensed under the MIT License. See the LICENSE file for details.