Skip to main content

​
Setting Up the Gumnut MCP Server

This guide walks you through configuring the Gumnut MCP server in popular AI tools.

​
Prerequisites

  1. A Gumnut account
  2. An API key (get one from the dashboard)
  3. An MCP-compatible tool

​
Server URL

The Gumnut MCP server is available at: 
https://mcp.gumnut.ai/mcp

​
Claude Code

Claude Code supports MCP servers natively through CLI commands or configuration files. Add the Gumnut MCP server with a single command: 
claude mcp add --transport http gumnut https://mcp.gumnut.ai/mcp \
  --header "Authorization: Bearer apikey_YOUR_API_KEY"
To make it available across all projects, add the --scope user flag: 
claude mcp add --transport http gumnut https://mcp.gumnut.ai/mcp \
  --header "Authorization: Bearer apikey_YOUR_API_KEY" \
  --scope user

​
Using JSON Configuration

Alternatively, add the configuration directly to your ~/.claude.json file: 
{
  "mcpServers": {
    "gumnut": {
      "type": "http",
      "url": "https://mcp.gumnut.ai/mcp",
      "headers": {
        "Authorization": "Bearer apikey_YOUR_API_KEY"
      }
    }
  }
}
For project-specific configuration, create a .mcp.json file in your project root with the same structure.

​
Verify Installation

Check that the server is configured: 
claude mcp list
You can also use the /mcp command within Claude Code to see available servers and their tools.

​
Cursor

Cursor supports MCP servers through JSON configuration files.

​
Configuration File Location

  • Global (all projects): ~/.cursor/mcp.json
  • Project-specific: .cursor/mcp.json in your project root

​
Configuration

Create or edit the configuration file: 
{
  "mcpServers": {
    "gumnut": {
      "url": "https://mcp.gumnut.ai/mcp",
      "transport": "http",
      "headers": {
        "Authorization": "Bearer apikey_YOUR_API_KEY"
      }
    }
  }
}

​
Using Cursor Settings UI

  1. Open Cursor and go to File > Preferences > Cursor Settings
  2. Select the MCP tab
  3. Click Add Server
  4. Enter the server details:
    • Name: gumnut
    • URL: https://mcp.gumnut.ai/mcp
    • Transport: http
  5. Add the Authorization header with your API key

​
Verify Installation

After configuration, go to Cursor Settings > MCP to see gumnut listed as a registered server. Click refresh if needed.

​
Claude Web (claude.ai)

Claude on the web supports remote MCP servers through the Integrations feature.
MCP integrations on Claude.ai require a paid plan (Pro, Max, Team, or Enterprise). Free accounts cannot connect to MCP servers—use Claude Code or Claude Desktop instead.

​
Setup Steps

  1. Go to claude.ai and sign in
  2. Click your profile icon and select Settings
  3. Navigate to the Integrations section
  4. Click Add Custom Integration
  5. Enter the Gumnut MCP server URL: 
    https://mcp.gumnut.ai/mcp
  6. When prompted for authentication, enter your API key in Bearer token format: 
    apikey_YOUR_API_KEY
  7. Save the integration

​
Using the Integration

Once configured, you can ask Claude to interact with your Gumnut library directly in chat: 
"Show me all my photo albums"
"Find photos from last month"
"Create an album called 'Favorites'"

​
ChatGPT

ChatGPT supports MCP servers through the Deep Research feature with custom connectors.
MCP integration in ChatGPT is currently available for Enterprise, Team, and Education plans only. Individual ChatGPT Plus users do not have access to this feature at this time.

​
Setup Steps

  1. Open ChatGPT and go to Settings
  2. Navigate to Connectors (under Developer or Advanced settings)
  3. Click Add Custom Connector
  4. Configure the connector:
    • Name: Gumnut
    • Server URL: https://mcp.gumnut.ai/mcp
    • Authentication: Bearer Token
    • Token: apikey_YOUR_API_KEY
  5. Save the connector

​
Using with Deep Research

Once configured, you can use Gumnut with ChatGPT’s Deep Research feature:
  1. Start a new chat
  2. Enable Deep Research mode
  3. Select your Gumnut connector
  4. Ask questions about your photo library

​
Refreshing the Connector

If you update your API key or the server adds new capabilities:
  1. Go to Settings > Connectors
  2. Click on your Gumnut connector
  3. Select Refresh to update the server metadata

​
Troubleshooting

Having issues? See the MCP Troubleshooting guide for common problems and solutions.

​
Next Steps

Once configured, you can interact with your Gumnut photo library through natural language. See the MCP Overview for example interactions and available operations.