20-minute walkthrough with 2–3 personalized examples on your real pages.
Email, chat, or 24/7 phone support included on every paid plan.
You can now connect Claude, ChatGPT or any other MCP-capable assistant straight to your Personyze account and work in plain conversation — ask how campaigns are doing, find where you’re losing traffic, build a campaign, pause an action, manage audiences. No exports, no copying between tabs, no code.
MCP (Model Context Protocol) is the open standard AI assistants use to work with outside services. Anthropic introduced it in November 2024; OpenAI adopted it in 2025, and by early 2026 there were over 10,000 active public MCP servers. The usual analogy is “USB-C for AI”: instead of every tool building a bespoke integration for every assistant, a tool exposes one MCP server and every compatible assistant can use it.
Personyze runs one. An assistant that connects to it reaches your account directly, under your account’s permissions — the same external API surface as the full-featured API.
Server URL: https://personyze.com/mcp/
Most assistants ask only for the URL and then walk you through signing in:
Tools that can’t open a browser — a script, an IDE plugin — can send a Personyze API key as a header instead:
Authorization: Bearer YOUR_API_KEY
A note on availability: Personyze is now listed in the Claude connector directory, so on Claude it is a one-click install rather than pasting a URL — see the announcement. On ChatGPT and other assistants it works today as a custom connector using the URL above. Both Claude and ChatGPT gate connectors by plan tier, so check yours if the connection screen never appears.
The wording is yours — these are kinds of question, not fixed commands.
It reads the daily performance summary per action — impressions, deliveries, clicks, dismissals, failures, your configured goals and revenue totals. It will decline to quote a click-through rate on a sample too small to mean anything and say so, rather than quoting it anyway.
Site-wide traffic for any date range by page, landing page, referrer, search term, device, city or country — with sessions, bounces, goals, goal value and time on page, plus the personalization impressions and clicks on those pages. Rates are computed after grouping and low-traffic rows are excluded when ranking by a rate, so a 100% bounce rate over three sessions doesn’t outrank a real problem.
Targeting comes back as readable rule text — “Include on current page: Contains /pricing and not Full URL contains login” — not raw configuration.
“How do I set up conversion tracking?” is answered from the knowledge base with links to the articles used; if the docs don’t cover it, the assistant says so and offers to open a support ticket rather than guessing — writing up what you were doing and what it already checked, so support doesn’t start from nothing.
Twenty-three tools cover campaigns and actions, analytics, audiences and visitor profiles, placeholders, docs search and support tickets. Anything the dedicated tools don’t cover falls through to personyze_api — the same REST objects available to any API client — so the assistant isn’t boxed in by the tool list.
personyze_api
Giving an assistant write access to your website deserves scrutiny. Three properties matter here:
For developers building a client rather than using a ready-made assistant, the server implements OAuth 2.1 (authorization code with PKCE/S256, public clients), dynamic client registration (RFC 7591), and discovery per RFC 9728 and RFC 8414, with scope personyze:full.
personyze:full
Personalization tools have always had a reporting problem: the data lives in one panel, the decision happens in someone’s head, and the change happens in a third place a week later. MCP collapses that. You can ask which pages leak sessions, get the answer from your real personalization data, and stage a campaign against that page — in the same conversation, without leaving your assistant.
It also means Personyze fits into whatever agentic stack you’re already assembling. Forrester expects 30% of enterprise app vendors to launch MCP servers in 2026; the practical upshot is that your assistant can read your CRM, your ads and your personalization platform side by side, and reason across them.
If you’d rather not leave the panel, the same capabilities exist as the built-in Personyze AI Agent.
It’s a Model Context Protocol server at https://personyze.com/mcp/ that lets Claude, ChatGPT or any MCP-capable assistant connect to your Personyze account and work with it in plain conversation – reading campaign performance and traffic analytics, building staged campaigns, pausing actions, and managing audiences and visitor profiles.
Copy the Server URL from Integrations → AI Assistants (MCP) in Personyze, then add it as a custom connector in your assistant – Claude: Settings → Connectors → Add custom connector; ChatGPT: Settings → Connectors. Approve the connection on the Personyze screen that opens; the assistant receives its own credential, so there is nothing to copy and paste.
Personyze is now live in the Claude connector directory, so on Claude it installs in one click. On ChatGPT it works as a custom connector using the server URL. Both assistants gate connectors by plan tier.
Not without you knowing. New campaigns are created in staging mode and shown only to visitors from a staging IP, so live traffic is unaffected until you publish. Pausing or resuming a live action is confirmed first in concrete terms – naming the action, its campaign, and what visitors will stop or start seeing – and is reversible.
It rides on an API key belonging to your account and acts with that account’s permissions, so it can see and change only what that account can. To disconnect, delete the key under Integrations → AI Assistants (MCP); revocation is immediate.
Both Claude and ChatGPT gate custom connectors by plan tier, so check your plan if the connection screen never appears. On the Personyze side the MCP server uses the same external API as the full-featured API, under your account’s permissions.
Only staging-mode campaigns can be renamed or re-targeted by an assistant – live campaigns are edited in the panel. It also won’t quote statistics from samples too small to be meaningful, and if the documentation doesn’t answer a question it offers to open a support ticket rather than guessing.
Connect your assistant and ask it what to fix this week. Book a demo or view plans.
See it in action on the AI personalization agent page.
Product overview: Personyze MCP server.
30 minutes with a personalization expert. Bring your stack, your goals, your skepticism. We'll show you what changes when every visit feels like the only one.