Dash Docs MCP Server

The Dash documentation site exposes a Model Context Protocol (MCP) server. This lets AI agents like Claude Code, Cursor, or any MCP-compatible client search and read docs directly from your development environment.

This is our recommended way of using Dash documentation with AI agents, notably because your agent will always have access to the latest documentation updates.

Connecting

Select your MCP client for setup instructions. All clients authenticate with your Plotly Cloud account in the browser the first time you use a tool.

Claude Code

Run the following command in your terminal to add the server globally (available across all your projects):

claude mcp add plotly-dash-documentation --transport http --scope user <a href="https://&lt;your-dash-enterprise-server&gt;/_mcp">https://&lt;your-dash-enterprise-server&gt;/_mcp</a>

Note: You need to restart Claude Code after running this command for the new MCP server to be available.

To authenticate, type /mcp in Claude Code, select the server, and select Authenticate. You’ll be prompted to sign in with your Plotly Cloud account in the browser.

Cursor

Open your Cursor MCP settings and add the following:

{
  "mcpServers": {
    "plotly-dash-documentation": {
      "type": "http",
      "url": "https://&lt;your-dash-enterprise-server&gt;/_mcp"
    }
  }
}

When you first use a tool, Cursor will open a browser window so you can sign in with your Plotly Cloud account.

Windsurf

Open your Windsurf MCP config file and add the following:

{
  "mcpServers": {
    "plotly-dash-documentation": {
      "type": "http",
      "url": "https://&lt;your-dash-enterprise-server&gt;/_mcp"
    }
  }
}

When you first use a tool, Windsurf will open a browser window so you can sign in with your Plotly Cloud account.

ChatGPT

ChatGPT supports custom remote MCP servers in developer mode (available on eligible plans).

In ChatGPT, go to Settings > Connectors and enable developer mode.
Add a new connector with:
- Name: Plotly Dash Documentation
- URL: https://<your-dash-enterprise-server>/_mcp
Complete the sign-in with your Plotly Cloud account when prompted.

Claude

In Claude (web or desktop), go to Settings > Connectors > Add custom connector and enter:

Name: Plotly Dash Documentation
URL: https://<your-dash-enterprise-server>/_mcp

Complete the sign-in with your Plotly Cloud account when prompted.

Note: Custom connectors require a paid Claude plan. See Building custom connectors via remote MCP servers.

Gemini CLI

Add the following to your ~/.gemini/settings.json:

{
  "mcpServers": {
    "plotly-dash-documentation": {
      "httpUrl": "https://&lt;your-dash-enterprise-server&gt;/_mcp"
    }
  }
}

Then start Gemini CLI and authenticate:

/mcp auth plotly-dash-documentation

A browser window will open so you can sign in with your Plotly Cloud account. For general setup, see the Gemini CLI MCP documentation.

Replit

In your Replit workspace, go to Integrations > MCP Servers and add a new server:

Name: Plotly Dash Documentation
URL: https://<your-dash-enterprise-server>/_mcp

Complete the sign-in with your Plotly Cloud account when prompted. For general setup, see the Replit MCP documentation.

Lovable

In Lovable, open Settings > Connectors and add a custom MCP server pointing at:

<a href="https://&lt;your-dash-enterprise-server&gt;/_mcp">https://&lt;your-dash-enterprise-server&gt;/_mcp</a>

Complete the sign-in with your Plotly Cloud account when prompted. For general setup, see the Lovable MCP documentation.

Figma Make

In a Figma Make file, select the + icon, then Connectors, and add a custom MCP server with the URL:

<a href="https://&lt;your-dash-enterprise-server&gt;/_mcp">https://&lt;your-dash-enterprise-server&gt;/_mcp</a>

Complete the sign-in with your Plotly Cloud account when prompted. For general setup, see Connect external tools to Figma Make using MCP.

Kiro

Open the Command Palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows/Linux) and search for “MCP”, or go to File > Settings to open your mcp.json, then add:

{
  "mcpServers": {
    "plotly-dash-documentation": {
      "type": "http",
      "url": "https://&lt;your-dash-enterprise-server&gt;/_mcp"
    }
  }
}

Save the file. When the server connects, sign in with your Plotly Cloud account in your browser if prompted. For general setup, see the Kiro MCP documentation.

Codex CLI

Add the server from your terminal:

codex mcp add plotly-dash-documentation --url <a href="https://&lt;your-dash-enterprise-server&gt;/_mcp">https://&lt;your-dash-enterprise-server&gt;/_mcp</a>

Follow the authentication flow when prompted to sign in with your Plotly Cloud account. For general setup, see the Codex CLI MCP documentation.

Other MCP clients

For any MCP-compatible client, point it at the following URL:

<a href="https://&lt;your-dash-enterprise-server&gt;/_mcp">https://&lt;your-dash-enterprise-server&gt;/_mcp</a>

Refer to your client’s documentation for how to add an HTTP-based MCP server. You will need to authenticate with your Plotly Cloud account before using the tools.

Don’t have a Plotly Cloud account yet? Create one here (it’s free!)

What Your Agent Can Do

Once connected, your AI agent can browse the full documentation, search for topics by keyword, and read the content of any page. You don’t need to tell it which tool to use—just ask your question and it will figure out the rest.

Available tools

Tool	Description
`list_pages`	List all available Dash documentation pages, each with its url, name, and description.
`search_pages`	Search documentation pages by keyword across page names, descriptions, and component prop keywords.
`get_page_as_markdown`	Retrieve the full rendered content of a documentation page by its URL path (for example, `/layout`). Enterprise-gated pages require a Plotly Cloud subscription.

Example Prompts

Open source:

“Build me a multi-page Dash app with a callback that filters an AG Grid”
“Add pattern-matching callbacks to my existing app”
“Set up background callbacks with a progress bar”
“I want to publish this app so other people can use it. How can I do that?”

Enterprise extensions (requires a Plotly Cloud for Enterprise plan):

“Build a dashboard using Dash Design Kit with a sidebar and header”
“Add Snapshot Engine to my app so users can export reports”
“Set this app up for Dash Enterprise deployment”
“Embed this Dash app in my React application”

Accessing Enterprise Content

Once authenticated, open-source Dash documentation is available to all users. Documentation for enterprise libraries (Design Kit, Snapshot Engine, Embedded, etc.) require a Plotly Cloud subscription with an Enterprise plan. If your account does not have the required entitlements, requests for these pages will return a message indicating a subscription is needed.