Selector AI MCP server

This repository provides a Model Context Protocol (MCP) server implementation for Selector AI, enabling streaming-capable interactions between applications and Selector's AI models. The server supports real-time streaming and interactive AI chat through a FastMCP-compatible Python implementation.

Prerequisites

To use the Selector MCP server, you'll need:

• Python 3.8 or newer
• Docker
• A Selector AI API Key
• Selector API URL

Installation

Clone the Repository

git clone https://github.com/automateyournetwork/selector-mcp-server
cd selector-ai-mcp

Install Python Dependencies

pip install -r requirements.txt

Set Environment Variables

Create a .env file with the following content:

SELECTOR_URL=https://your-selector-api-url
SELECTOR_AI_API_KEY=your-api-key

Build the Docker Image

docker build -t selector-mcp .

Using the Client

Start the Client

Launch the interactive shell that communicates with the Selector AI:

python mcp_client.py

Example CLI Session

Once connected, you can have interactive conversations:

You> What is AIOps?
Selector> AIOps refers to the application of AI to IT operations...

Programmatic Access

You can also use the client programmatically in your Python code:

from selector_client import call_tool, spawn_server

# Start the server process
proc = spawn_server()

# Check if server is ready
call_tool(proc, "ready")

# Send a query to Selector AI
response = call_tool(proc, "ask_selector", {"content": "What is AIOps?"})

print(response)

Using with Claude Desktop

If you're integrating with Claude Desktop:

Run the Server

python mcp_server.py

Connect to the Server

Configure Claude Desktop to connect to the local socket or HTTP endpoint.

Message Format

Ensure your messages match this format:

{
  "method": "tools/call",
  "tool_name": "ask_selector",
  "content": "What can you tell me about device S6?"
}

Building a Custom Container

To customize the MCP server:

1. Fork or clone the repository
2. Modify the selector_fastmcp_server.py file to integrate your preferred model or routing logic
3. Rebuild the Docker image:

docker build -t my-custom-mcp .

4. Update the client to use your custom image by changing:

"docker", "run", "-i", "--rm", "my-custom-mcp"

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "selector-ai" '{"command":"docker","args":["run","-i","--rm","selector-mcp"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "selector-ai": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "selector-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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "selector-ai": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "selector-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect