Skip to content
Your AI agent

Entagl MCP

Manage your workspace by chatting with Claude or OpenAI Codex, from anywhere.

1 Your connection link, with a Copy button. 2 Download the skill guide. Screenshot taken 10 November 2026.

Overview

The Entagl MCP connects Entagl to your own AI assistant, Claude or OpenAI Codex, so you can run your business by talking to it from wherever you already work. Ask what your AI is set up to do, add FAQs, change prices, update your hours or create an offer, all in plain language. You can also ask it to analyze your conversations and find out why your AI answered the way it did.

Changes go live in your workspace right away. There is nothing to approve afterwards. When you change how your AI behaves, Entagl runs a quick safety check first. It's free on every plan, takes about a minute to set up, and is available to the workspace owner.

Features

Your workspace, inside your AI assistant

MCP (Model Context Protocol) is a secure way to connect an app to an AI assistant. Connecting the Entagl MCP lets Claude or OpenAI Codex read and update your Entagl workspace for you, and analyze or debug your AI's conversations when you ask. It can do the same things Maya does inside Entagl, plus deeper conversation analysis.

See how your AI is set up

Ask questions like "what is my AI agent set up to do?" or "list my services and prices". Your assistant reads your current setup and answers in plain language. Nothing is changed.

Make changes by asking

Tell your assistant to add a FAQ, change a price, update your business hours, refine your agent's instructions or create an offer, and it makes the change for you. It reads the current details first so the change fits what's already there.

Review and debug your conversations

Ask your assistant to analyze your conversations: "what happened this week?", "which customers dropped off after hearing the price?", "why didn't it book that customer?". It can find conversations by customer name, phone number or Instagram handle, read the transcripts, and see what your AI did behind the scenes, such as which tools it used. Then it can fix the problem with you and try the fix in a safe dry run before any customer sees it. Because conversations contain customer-written text, once your assistant has read them it shows you each change and waits for your yes in the chat before applying it.

Applied straight away, with a safety check

There's no separate approval screen. A change you ask for goes live in your workspace straight away. When you change how your AI agent behaves (its instructions), Entagl first runs a quick safety check against your live setup and only applies the change if it passes. Your assistant tells you exactly what happened either way.

Download the skill

On the Entagl MCP settings page, click Download the skill guide to get a short playbook for your assistant. It teaches the analyze, debug, fix and verify routine and keeps changes safe: look first, one change at a time. Add it to Claude as a Skill, or to your project as instructions for Claude Code or Codex. It's optional; the connection works without it.

Scoped to you, with an audit trail

You sign in with your Entagl account, so the connection only ever touches your own workspace. Conversation content is shared with your AI assistant only when you ask it to read or analyze conversations, and every such read is recorded in an access log. Connection secrets and passwords are never shared.

Common tasks

Connect the Entagl MCP

About 3 min
  1. In Entagl, go to Settings → Entagl MCP and click Copy next to Your connection link.
  2. In Claude, open Settings → Connectors → Add custom connector. In OpenAI Codex, add Entagl as an MCP server.
  3. Paste your connection link and confirm.
  4. Sign in with your Entagl account when your assistant asks. That links it securely to your workspace, and you're ready to go.

Tips

It's free on every plan and takes about a minute to set up.
Connecting is easiest from your computer. On a phone, copy the link and open it in your AI app there.
Start by asking "what is my AI agent set up to do?" to see a summary of your setup before you change anything.
Changes apply right away, so there's nothing to approve later. Every change is recorded, and you can ask your assistant to change anything back.

Frequently asked questions

Was this page helpful?