Prem MCP Server

A Model Context Protocol (MCP) server implementation for Prem AI, enabling seamless integration with Claude and other MCP-compatible clients. This server provides access to Prem AI's powerful features through the MCP interface.

Features

• 🤖 Chat Completions: Interact with Prem AI's language models

• 📚 RAG Support: Retrieval-Augmented Generation with document repository integration

• 📝 Document Management: Upload and manage documents in repositories

• 🎭 Template System: Use predefined prompt templates for specialized outputs

• ⚡ Streaming Responses: Real-time streaming of model outputs

• 🛡️ Error Handling: Robust error handling and logging

Prerequisites

• Node.js (v16 or higher)

• A Prem AI account with API key

• A Prem project ID

Installation

Installing via Smithery

To install prem-mcp-server for Claude Desktop automatically via Smithery:

Installing Manually

Configuration

1. Environment Variables

Create a .env file in your project root:

2. Cursor Configuration

To use the Prem MCP server with Cursor, add the following to your ~/.cursor/mcp.json:

Replace /path/to/your/prem-mcp with the actual path to your project directory.

3. Claude Desktop Configuration

For Claude Desktop users, add the following to your claude_desktop_config.json:

Usage

Starting the Server

Example Prompts

1. Basic Chat

2. RAG with Documents

3. Using Templates

Document Upload

The server supports uploading documents to Prem AI repositories for RAG operations. Supported formats:

• .txt

• .pdf

• .docx

API Reference

Chat Completion Parameters

• query: The input text

• system_prompt: Custom system prompt

• model: Model identifier

• temperature: Response randomness (0-1)

• max_tokens: Maximum response length

• repository_ids: Array of repository IDs for RAG

• similarity_threshold: Threshold for document similarity

• limit: Maximum number of document chunks

Template Parameters

• template_id: ID of the prompt template

• params: Template-specific parameters

• temperature: Response randomness (0-1)

• max_tokens: Maximum response length

Development

Troubleshooting

Common Issues

1. Server Not Found

   • Verify the server path in claude_desktop_config.json

   • Check if the server is running

2. API Key Invalid

   • Ensure your Prem AI API key is valid

   • Check if the API key has the required permissions

3. Document Upload Failed

   • Verify file format is supported

   • Check file permissions

   • Ensure repository ID is correct

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see the LICENSE file for details.

Acknowledgments

• Prem AI for their powerful AI platform

• Model Context Protocol for the protocol specification

• Anthropic for Claude and the MCP ecosystem

Support

For issues and feature requests, please use the GitHub Issues page.