Skip to main content

Quick Start

Updated on 3 November 2026.

Add an MCP server, choose what agents may call, connect an AI app and review the first tool calls.

Add an MCP
Library: Install or Set up
Or Add MCP server
Configure
Policy Engine or classic settings
Tools, guardrails and access
Connect your AI app
OneMCP URL
Or the server's Quilr gateway URL
Monitor
Insights and individual tool calls
QuilrAI

Video walkthrough​

MCP Gateway: administrator overviewConsole walkthrough4:59

Registering servers, governing which tools agents can call, reading the audit trail, and handing the gateway to your users.

YouTube All videos

The rest of the series: the user dashboard for the people who will use the MCPs, and local setup for administrators and for users.

1. Add an MCP​

Go to Settings > AI Gateway > MCP Gateway.

To addDo this
A ready-made integrationClick Library, search, then click Install (or Set up when it asks for a key or OAuth app). See MCP Library.
Your own remote serverClick Add MCP server, choose Remote server, enter its Transport URL and click Probe and continue. See Adding MCP Servers.
A REST APIClick Add MCP server, then choose API. See API to MCP.
A package that runs on the user's computerClick Add MCP server, then choose Local package (CLI MCP). See Local MCP.

If the server uses OAuth, a banner asks for an administrator connection. Click Review all (or Connect OAuth on the card) and sign in once so the gateway can discover its tools.

2. Configure​

After you add a server, review who can connect and which tools they may call before connecting users. Choose the mode that governs your MCP Gateway.

With the engine on, open Govern > Policy Engine > MCP Gateway and review the matching rules:

  1. MCP Server Access decides who may connect.
  2. Invocation & Discovery decides which tools are listed, may run and may return results. Select a recipe such as Allow selected tools and choose the server and tools.
  3. Data & Adversarial Risks selects checks and actions for tool arguments and results. Use Human Confirmation where a caller must approve a tool call.
  4. Save changes to the shared draft, use Test, then Review & publish.

Check existing matching rules before adding new ones. Published policies govern the marked settings sections; editing their classic values does not change live policy behavior. See Author, simulate and publish and Tool visibility.

3. Connect your AI app​

Users sign in at mcpgateway.quilr.ai, connect their accounts and copy a URL from there.

URLUse it for
OneMCP, https://mcpgateway.quilr.ai/quilrone/mcpEvery MCP the user may use, through one connection. See OneMCP.
Quilr gateway URL from the server card, https://mcpgateway.quilr.ai/<slug>/mcpOne server only

The base domain can differ by environment. Copy the exact URL from the server card or the user dashboard.

OAuth-capable clients such as Claude and ChatGPT sign in when they first connect. For a client that sends a token instead, create one in the server's Settings > API tokens (see API Tokens) and send it with the user's email:

{
"mcpServers": {
"quilr-mcp": {
"url": "https://mcpgateway.quilr.ai/<your-mcp-slug>/mcp",
"headers": {
"Authorization": "Bearer <your-token>",
"mcpuser": "user@company.com"
}
}
}
}

See the Integration Guide for more client examples.

4. Monitor​

Select Overall analytics to open MCP Gateway Insights.

TabCheck
OverviewCalls, people, failures, detections and attention items
UsageAdoption and new or returning users
Data & securityWhat AI touched or changed and flagged content
ReliabilityFailure causes, affected tools and input problems
Servers & toolsServer health, tool use and savings

For an individual call, return to a server card and select Inspect > Logs. The operational Activity > Tool calls view shows its user, agent and outcome. Select a call for its details. See Analytics and insights for the full tour.

To send logs to your own data platform, use the Log Export API.