From the maker

Agentzia simulates users researching products with ChatGPT, Claude, Gemini, and Grok. Its hosted MCP lets coding agents run studies, inspect recommendation decisions and supporting evidence, and identify website improvements. Seven tools cover studies, report retrieval, retries, and credit management. Connect over Streamable HTTP with browser OAuth; an Agentzia account is required. New accounts receive complimentary credits; additional research uses paid credits. Each selected assistant uses one channel credit. The public MIT-licensed repository contains client plugin manifests and the agentzia-optimize workflow skill; the hosted research service is separate.

How to connect

Streamable HTTP endpoint:

https://www.agentzia.dev/mcp

What happened when we asked

We asked on 20 September 2026 and it challenged us for credentials. That is a working server guarding itself: it answered, and it wants an account we do not hold. A tool count and a response time come from a tools/list we were never served, so this listing carries neither.

How it asks you to sign in

Its refusal named a public document describing how to authenticate, which is what the MCP authorization spec asks a guarded server to publish. We read that document on 20 September 2026. Everything below is what it says; we have still not been inside this server.

It calls itself

Agentzia MCP

Sign in through

atcrnblkgoqjaxjdrjyi.supabase.co

Token accepted in

header

Read

2026-09-20 17:56 UTC

The 1 permission it declares

These are the scopes the document lists, verbatim. They describe what an account can grant this server, not what it will do with the grant, and we have not audited either.

• email

Anything above describes one moment on the date shown. We do not re-test on a schedule, so nothing here says what this server is doing now. We have not audited its code, its data handling or its permissions, and this is not a safety rating.