Setup

Getting Started

neuroflash offers an MCP server that connects AI assistants to the neuroflash API. It runs as a remote HTTP Streaming Transport server — there is nothing to download or install locally. You just point your MCP client to the server URL and authenticate with your neuroflash account.

Currently available on QA at https://app-qa.neuroflash.com/api/mcp-server/v1/mcp. Production URL will be https://app.neuroflash.com/api/mcp-server/v1/mcp.

Claude Desktop

Claude Desktop has built-in support for remote MCP servers. To connect:

1. Open Settings (gear icon)
2. Go to Connectors
3. Click Add
4. Enter the server URL: https://app-qa.neuroflash.com/api/mcp-server/v1/mcp
5. Save and connect

Authentication happens automatically — Claude Desktop will open a browser window where you log in with your neuroflash account. Once logged in, the session is established and you can start using the tools immediately.

Cursor

Add the following to .cursor/mcp.json in your project root (or global Cursor MCP config):

{
  "mcpServers": {
    "neuroflash": {
      "url": "https://app-qa.neuroflash.com/api/mcp-server/v1/mcp"
    }
  }
}

When you first use the server, Cursor will prompt you to authenticate via your browser.

Other MCP Clients

Any MCP client that supports HTTP Streaming Transport can connect to the neuroflash MCP server. Just provide the server URL:

https://app-qa.neuroflash.com/api/mcp-server/v1/mcp

The server implements standard OAuth 2.0 with PKCE for authentication. Your client will handle the login flow automatically.

MCP_MODE Options

The MCP_MODE setting controls which interaction styles are available to the LLM. This is configured by the server administrator, not by end users.

smart is a composition of code and layered — it registers the 5 alternative-mode tools without the 46 traditional tools. all registers everything and is the default.