LogZuno runs a Model Context Protocol server at https://platform.logzuno.app/mcp. AI assistants connect with OAuth 2.1: the first time, your browser opens LogZuno, you sign in and approve the connection. The assistant then acts as you, within your role in each organisation: viewers can read; members and above can also create alerts and send events. Disconnect an assistant at any time under Settings → API tokens → Connected apps.
The steps below were checked against each client's documentation on 23 October 2026. Menus move between versions; the URL and OAuth are what every client needs.
Claude
Claude.ai, Claude Desktop and Cowork, on Pro and Max: Customize → Connectors, then + Add → Add custom connector. Name it LogZuno, enter https://platform.logzuno.app/mcp, continue with sign-in on, and Add. Turn it on in a conversation from + → Connectors.
On Team and Enterprise plans an owner adds it first under Organization settings → Connectors → Add → Custom → Web; each member then connects their own account. Claude connects from Anthropic's servers, so this works with LogZuno's public address and nothing to install. (Source: Claude Help Center, "Get started with custom connectors using remote MCP".)
ChatGPT
Custom MCP servers are available on ChatGPT Business and Enterprise/Edu, on the web; Pro users can connect with read and fetch permissions only. Open Plugins, select + → Add custom MCP server, enter a name and https://platform.logzuno.app/mcp, choose OAuth, accept the risk warning and select Create as a plugin. Use it in a chat by typing @ and choosing LogZuno. (Source: OpenAI Help Center, "Connecting custom MCP servers in ChatGPT".)
Cursor
Add LogZuno to ~/.cursor/mcp.json, or to .cursor/mcp.json in a project:
{
"mcpServers": {
"logzuno": { "url": "https://platform.logzuno.app/mcp" }
}
}Cursor supports OAuth for remote servers: sign in to LogZuno when it asks. (Source: cursor.com/docs/context/mcp.)
VS Code
Open the Command Palette, run MCP: Add Server, choose HTTP, enter https://platform.logzuno.app/mcp and the ID logzuno, then Global → Copilot Global for a personal setup. (Source: VS Code docs, "Add MCP servers in VS Code".)
Tools
| Tool | What it does |
|---|---|
list_projects | The projects you can use, with their IDs |
query_events | Raw events, newest first, by event, channel or user |
run_chart | Runs a chart spec (trends, number, table, users, frequency, funnel, retention) and returns the result with a written summary |
ask | Answers a question in plain language with a chart |
get_dashboard | A dashboard with every tile's current data |
get_web_analytics | Web traffic by audience (people, unconfirmed, all) and channel |
get_ai_visibility | The AI visibility report: fetches, verification, impostors and visits from AI |
list_users | Users in a built-in segment or by search |
get_user | One user's profile, activity and latest events |
create_alert | Creates an event, threshold or report alert |
log_event | Sends an event, like POST /v1/log |
Resources: logzuno://guides/chart-spec (how to write chart specs), and for each project its catalogue (event names, property keys, channels, destinations) and dashboards.
Things to ask
- "In LogZuno, how many people signed up each week this quarter, by plan?"
- "Which pages did ChatGPT fetch most this month, and how many visits came from it?"
- "Create an alert that posts to Slack when a payment fails."