Storm MCP server

Serverless RAG implementation using FastAPI that provides flexible file upload, processing, and tool integration capabilities with a modular server architecture for dynamic resource management.
Back to servers
Provider
Sionic AI
Release date
Mar 11, 2025
Language
Python
Stats
36 stars

The Storm MCP Server integrates the Sionic AI Storm Platform with Claude Desktop through Anthropic's Model Context Protocol (MCP). This implementation enables seamless interaction between LLM applications and RAG (Retrieval-Augmented Generation) data sources, allowing you to build powerful serverless RAG solutions without the need for complex infrastructure.

Installation Instructions

Prerequisites

  • Claude Desktop application installed
  • A Storm Platform account and API token from sionicstorm.ai

Setting Up the Server

  1. Clone the repository to your local machine:
git clone https://github.com/sionic-ai/serverless-rag-mcp-server.git
cd serverless-rag-mcp-server
  1. Add your Storm API Key to the run script:
# Open the run.sh file
nano scripts/run.sh

# Add your API key to the STORM_API_KEY variable
# It should look like:
export STORM_API_KEY='your-api-key-here'
  1. Configure Claude Desktop to connect to the MCP server:
# Open the Claude Desktop configuration file
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
  1. Add the MCP server configuration to the JSON file:
{
  "mcpServers": {
    "storm": {
      "command": "sh",
      "args": [
        "/path/to/your/serverless-rag-mcp-server/scripts/run.sh"
      ]
    }
  }
}

Make sure to replace /path/to/your/ with the actual path to where you cloned the repository.

  1. Save the configuration file and restart Claude Desktop.

Using the MCP Server

Available Tools

The Storm MCP Server provides several tools for interacting with the Storm Platform:

  • send_nonstream_chat - Send messages to the Storm AI platform
  • list_agents - View available agents in your Storm account
  • list_buckets - View document buckets for storage
  • upload_document_by_file - Upload documents to use in your RAG system

Uploading Documents

To upload a document to the Storm Platform:

  1. In Claude Desktop, initialize a conversation with your MCP server.
  2. Upload a file through the Claude interface.
  3. The document will be processed and stored in your Storm account.

Creating RAG Queries

After uploading documents, you can ask questions about their content:

  1. In Claude Desktop, ensure your MCP server is connected.
  2. Ask questions related to your uploaded documents.
  3. The system will retrieve relevant information from your documents and use it to enhance Claude's responses.

Viewing Available Resources

To see what agents and buckets are available in your account:

  1. Ask Claude to list your agents: "Can you list my Storm agents?"
  2. Ask Claude to list your document buckets: "Show me my available Storm buckets."

Managing Documents

You can:

  • Upload new documents through the interface
  • Reference specific documents in your queries
  • Create different buckets for organizing your documents

Troubleshooting

  • If Claude cannot connect to the MCP server, check that the path in your configuration file is correct.
  • Ensure your API key is correctly set in the run.sh file.
  • Verify that Claude Desktop has been restarted after configuration changes.
  • Check that your Storm Platform account is active and has the necessary permissions.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later