Skip to main content
Connect Claude, ChatGPT, Cursor, or another AI tool to Kadoa over the Model Context Protocol. Then ask it to create workflows, read data, or set up alerts in plain language.
Server URL

​
Choose your AI tool

Claude

ChatGPT

Gemini

Claude Code

Codex

Cursor

Claude Desktop

Antigravity CLI

Other clients

​
How it works

  • Your AI tool calls Kadoa’s tools. It reads data, lists workflows, and changes settings.
  • Kadoa’s agent builds and repairs workflows. When your AI tool asks for a new workflow or a fix, the agent does the work, as it does in the dashboard.
The server is hosted by Kadoa and follows the authenticated remote MCP spec. After setup, try the example prompts. For every tool your AI tool can call, see MCP tools.

​
Setup

​
General

The server is centrally hosted and managed by Kadoa, using Streamable HTTP as its transport. There is nothing to install and no API key to manage. To run the server locally over stdio instead, use npx -y @kadoa/mcp. There are two ways to connect:
  • Personal connection (https://mcp.kadoa.com/mcp): You sign in with your own Kadoa account, and every tool call runs as you, under your role and active team. Best for individual use.
  • Service connector (https://service.mcp.kadoa.com/mcp): A workspace admin generates OAuth credentials once, and applications or organization members connect as a shared workspace service account, with no Kadoa login. Best for organization-wide rollouts and app contexts where nobody can sign in interactively. See MCP Service Connector →.
For a personal connection, add the server in your client: a browser opens so you can sign in with your Kadoa account and grant access. The connection then stays authorized; if a session expires, your client prompts you to sign in again.
With a personal connection, the MCP server acts as you: every tool runs under your Kadoa role and active team, and each action is recorded in the workflow’s history.
Instructions for specific clients follow below.

​
Other clients

Any MCP-compatible client can connect with the following settings:
  • URL: https://mcp.kadoa.com/mcp
  • Transport: Streamable HTTP
  • Auth: OAuth (sign in with your Kadoa account)

​
Common use cases

Once connected, you manage the full workflow lifecycle through natural conversation. Copy an example prompt into your client to explore what’s possible. For the full list of tools your AI tool can call, see MCP tools.
Create a workflow that extracts product name, price, and rating from https://sandbox.kadoa.com/ecommerce, run it, and show me the first results.
Set up a workflow that scrapes competitor prices from https://sandbox.kadoa.com/ecommerce daily at 6:00, and email me when a run finishes or fails.
Show me all changes my real-time monitors detected this week and summarize what moved.
Export the full ‘Product Monitor’ dataset and analyze price trends by category.
Update the ‘Product Monitor’ schema to add a rating field, then pause the old ‘Legacy Scraper’ workflow.
My Product Monitor is waiting for my answer. Show me the question, then answer it: use the US store.
Save ‘Product Monitor’ as a template called ‘Product Scraper’, then create a workflow from it for each of these five store URLs.
Which workflows need attention, which ones are failing, and what changed across my team this week?
Which team is active, and who changed my workflows this week?
Fetch https://sandbox.kadoa.com/ecommerce as markdown and summarize what’s on the page.
My ‘Product Monitor’ keeps failing. Look at the last failed run, and if it’s a Kadoa issue, file a support ticket.

​
Troubleshooting

​
I don’t have access to Kadoa

  • Verify the MCP server is configured in the correct config file
  • Restart your MCP client after configuration changes
  • Re-authenticate via OAuth if prompted

​
Authentication failed

  • Your OAuth session may have expired, so re-authenticate when prompted by your MCP client
  • A connection is fixed to the team you chose at sign-in. To use another team, remove the connector, add it again, and choose that team when you sign in. Use team_list to see the active team.