MCP Setup

Setting Up the Gumnut MCP Server

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

Prerequisites

A Gumnut account
An MCP-compatible tool

Any MCP client

Gumnut runs a standard remote MCP server over HTTP, so a client that supports remote MCP servers can connect to it — provided it can also authenticate. Every HTTP request to the server carries your Gumnut credentials, including protocol initialization when your client uses it, tool discovery, notifications, and tool calls. Remote transport on its own isn’t enough: your client needs to support either the MCP OAuth flow or configurable request headers. The same endpoint supports both modern sessionless MCP clients and legacy clients that use the initialize handshake. You don’t need a separate URL or sticky-session configuration; use the HTTP transport option your client documents. If a request is missing a credential or carries an invalid, expired, or revoked bearer, the server returns 401 Unauthorized with a WWW-Authenticate OAuth challenge. OAuth-capable clients can follow that challenge to discover the sign-in flow. Clients using an API key must send it in the Authorization header on every request, not only on tool calls. The tools below have step-by-step instructions because they’re the ones people ask about most, not because they’re the only ones that work. To connect a client that isn’t listed, you need two things. The server URL:

https://api.gumnut.ai/mcp

Authentication, in one of two forms:

OAuth — if your client can sign in to remote MCP servers, point it at the URL and it will open a browser window to authorize your Gumnut account. Nothing else to configure.
An API key — if your client can’t do OAuth, or the sign-in flow gives you trouble, send the key as an Authorization header instead.

Most clients configure servers with JSON in roughly this shape:

{
  "mcpServers": {
    "gumnut": {
      "url": "https://api.gumnut.ai/mcp",
      "headers": {
        "Authorization": "Bearer apikey_YOUR_API_KEY"
      }
    }
  }
}

Drop the headers block if you’re using OAuth. The exact keys vary between clients — some want an explicit transport field such as "type": "http" or "transport": "http" alongside the URL — so check your client’s documentation for its spelling.

Claude Code

Claude Code supports MCP servers natively through CLI commands or configuration files. When you connect, you’ll be prompted to authenticate with your Gumnut account via OAuth.

Using the CLI (Recommended)

Add the Gumnut MCP server with a single command:

claude mcp add --transport http gumnut https://api.gumnut.ai/mcp

To make it available across all projects, add the --scope user flag:

claude mcp add --transport http gumnut https://api.gumnut.ai/mcp --scope user

Using JSON Configuration

Alternatively, add the configuration directly to your ~/.claude.json file:

{
  "mcpServers": {
    "gumnut": {
      "type": "http",
      "url": "https://api.gumnut.ai/mcp"
    }
  }
}

For project-specific configuration, create a .mcp.json file in your project root with the same structure.

You can also authenticate with an API key instead of OAuth by adding an Authorization header:

claude mcp add --transport http gumnut https://api.gumnut.ai/mcp \
  --header "Authorization: Bearer apikey_YOUR_API_KEY"

Or in JSON configuration:

{
  "mcpServers": {
    "gumnut": {
      "type": "http",
      "url": "https://api.gumnut.ai/mcp",
      "headers": {
        "Authorization": "Bearer apikey_YOUR_API_KEY"
      }
    }
  }
}

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. When you connect, you’ll be prompted to authenticate with your Gumnut account via OAuth.

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://api.gumnut.ai/mcp",
      "transport": "http"
    }
  }
}

Using Cursor Settings UI

Open Cursor and go to File > Preferences > Cursor Settings
Select the MCP tab
Click Add Server
Enter the server details:
- Name: gumnut
- URL: https://api.gumnut.ai/mcp
- Transport: http

You can also authenticate with an API key instead of OAuth by adding an Authorization header to the configuration:

{
  "mcpServers": {
    "gumnut": {
      "url": "https://api.gumnut.ai/mcp",
      "transport": "http",
      "headers": {
        "Authorization": "Bearer apikey_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

Sign in to Claude. See Claude’s custom connector guide for the plan-specific navigation below.
Add the connector:
- Pro and Max: Open Customize > Connectors, click +, then select Add custom connector.
- Team and Enterprise: An Owner or Primary Owner must open Organization settings > Connectors, choose Add > Custom > Web, and add the connector. After it is configured, members open Customize > Connectors and select the connector.
Enter the Gumnut MCP server URL:
https://api.gumnut.ai/mcp
You’ll be prompted to authenticate with your Gumnut account via OAuth
Save the connector

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

Connect your photo library with the Gumnut plugin in ChatGPT.

Setup Steps

Open the Gumnut plugin in ChatGPT.
Follow the prompts to connect your Gumnut account and authorize access to your photo library.

Using Gumnut in ChatGPT

Once configured, you can ask ChatGPT to interact with your Gumnut photo library directly in chat.

Local and self-hosted models

You can use Gumnut with a model running on your own hardware:

The model generates the responses. It can run locally or in the cloud.
The MCP client is the app that connects to Gumnut and calls its tools on the model’s behalf.

Gumnut’s MCP server is cloud-hosted either way. Running the model locally doesn’t move your library or the API onto your machine — the client still reaches out to https://api.gumnut.ai/mcp over the network, and still authenticates as your Gumnut account. How you connect depends on which layers your local setup covers:

Apps that run models and act as an MCP client, such as LM Studio, need nothing extra from Gumnut. Add the server using the Any MCP client instructions and your local model can call Gumnut’s tools.
Runners that only serve models, such as Ollama, have no MCP client of their own. Pair one with a separate MCP client and point that client at Gumnut. Ollama, for instance, documents running Claude Code against a local Ollama instance — from there, follow the Claude Code section above.

What to expect

Gumnut exposes a broad set of tools, and choosing between them is the hard part for a model:

Use a tool-calling model with a generous context window. Smaller models tend to pick the wrong tool, or ignore the tools entirely, as the list grows.
Image understanding needs more than a vision model. For view_asset to work, the model has to be vision-capable and the client has to pass image results from tools back to the model. Clients that only forward text will leave the assistant working from metadata alone.
Interactive MCP Apps widgets are client-side. Clients that don’t implement MCP Apps still get every tool — they render the results as text rather than as photo grids and album cards.

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.

Getting started

Authentication

APIs

SDKs

MCP

Immich

More

Setting Up the Gumnut MCP Server

Prerequisites

Any MCP client

Claude Code

Using the CLI (Recommended)

Using JSON Configuration

Verify Installation

Cursor

Configuration File Location

Configuration

Using Cursor Settings UI

Verify Installation

Claude Web (claude.ai)

Setup Steps

Using the Integration

ChatGPT

Setup Steps

Using Gumnut in ChatGPT

Local and self-hosted models

What to expect

Troubleshooting

Next Steps

​Setting Up the Gumnut MCP Server

​Prerequisites

​Any MCP client

​Claude Code

​Using the CLI (Recommended)

​Using JSON Configuration

​Verify Installation

​Cursor

​Configuration File Location

​Configuration

​Using Cursor Settings UI

​Verify Installation

​Claude Web (claude.ai)

​Setup Steps

​Using the Integration

​ChatGPT

​Setup Steps

​Using Gumnut in ChatGPT

​Local and self-hosted models

​What to expect

​Troubleshooting

​Next Steps

Setting Up the Gumnut MCP Server

Prerequisites

Any MCP client

Claude Code

Using the CLI (Recommended)

Using JSON Configuration

Verify Installation

Cursor

Configuration File Location

Configuration

Using Cursor Settings UI

Verify Installation

Claude Web (claude.ai)

Setup Steps

Using the Integration

ChatGPT

Setup Steps

Using Gumnut in ChatGPT

Local and self-hosted models

What to expect

Troubleshooting

Next Steps