Use Kubera with AI Assistants: MCP Setup Guide

Ask ChatGPT, Claude, Perplexity, Gemini etc. about your net worth, assets, liabilities, and portfolio allocation using your live Kubera portfolio data.

Jump to

ChatGPT

Go to ChatGPT web

Click on Plugins in the left sidebar

Click the '+' button next to the plugins search bar

Field Value
Name kubera
Connection https://api.kubera.com/api/v1/mcp
Authentication OAuth

Check the 'I understand and want to continue' option and click 'Create'

You will be redirected to Kubera to Authenticate your account.

Once done, Start a new chat > Ask What's my net worth   

Claude

Go to Claude (web or app) sidebar menu

Customize > Connectors > + Add Custom Connector

Field Value
Name kubera
Remote MCP Server URL https://api.kubera.com/api/v1/mcp

Click Add.

Kubera will now appear in your Connectors list.

Select Kubera > Connect > Authorize

Start a new chat > Ask What's my net worth     

Grok

Go to the Grok sidebar menu

Skills and Connectors > New Connector > Custom

Field Value
Name kubera
Server URL https://api.kubera.com/api/v1/mcp

Click 'Add Connector'

In the next screen, enter Client ID as kubera-grok

Save & Connect

Authorize your Kubera account when prompted

Start a new chat > Ask What's my net worth     

Perplexity

Step 1: Generate AUTH_TOKEN in Kubera

Kubera (on desktop) > Settings > AI Assistants > Create MCP Auth Token

Step 2: On Perplexity

Go to Customize > Connectors > + Add Custom connector (Only available on premium plans)

Field Value
Name kubera
MCP Server URL https://api.kubera.com/api/v2/mcp
Advanced / Auth API Key
API Key AUTH_TOKEN (see Step 1 above)

Click Add. Kubera will appear as 'Connected'

Note: Perplexity assumes the token type, so paste only the auth token value — do not prefix it with 'Basic'. Kubera handles this automatically on its end.

Gemini CLI

Step 1: Generate AUTH_TOKEN in Kubera

Kubera (on desktop) > Settings > AI Assistants > Create MCP Auth Token

Step 2: In Gemini CLI

ADD
gemini mcp add --transport http kubera https://api.kubera.com/api/v2/mcp --header "Authorization: Basic <AUTH_TOKEN>"










REMOVE
gemini mcp remove kubera

Note: Kubera is not yet available on the Gemini consumer web/app versions. Export portfolio as LLM friendly markdown file, drop in Gemini and ask questions. Details below.

Codex App

Step 1: Generate AUTH_TOKEN in Kubera

Kubera (on desktop) > Settings > AI Assistants > Create MCP Auth Token

Step 2: In Codex

Field Value
MCP Server Name kubera
Transport Type Streamable HTTP
URL https://api.kubera.com/api/v2/mcp
Header key Authorization
Header value Basic AUTH_TOKEN (see Step 1 above)
  • Replace the entire <AUTH_TOKEN>  placeholder with the token you generated in Kubera desktop:
  • See step 1 above to know how to generate AUTH_TOKEN
  • Keep the word Basic in front of the token.
  • For example, if your token is abc123yourtokenhere , the Authorization header value should be: Basic abc123yourtokenhere           
  • Click Save.

Export Portfolio Data as MD

Alternatively, you can export an LLM-friendly markdown version of your portfolio data and use it with any AI Assistant whenever you need.

Kubera (on desktop) > Share menu (on the header) > Data for AI Assistants

Drop the file into ChatGPT, Claude, or Gemini and ask:

  • What stands out in my balance sheet?
  • Where am I overly concentrated?
  • Summarize my assets, liabilities, and entities
  • What questions should I ask my advisor?

You can also use it with private, local AI tools on your own machine.

Drop it into Ollama, LM Studio, or your personal knowledge base and let your AI work from your actual financial picture.

Related Articles