Quick Start

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

Tools: enable what agents may call

Guardrails, rules, access

Connect your AI app

OneMCP URL

Or the server's Quilr gateway URL

Monitor

Analytics, Activity, Health

QuilrAI

Video walkthrough

MCP Gateway: administrator overview4:59

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

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 add	Do this
A ready-made integration	Click Library, search, then click Install (or Set up when it asks for a key or OAuth app). See MCP Library.
Your own remote server	Click Add MCP server, choose Remote server, enter its Transport URL and click Probe and continue. See Adding MCP Servers.
A REST API	Click Add MCP server, then choose API. See API to MCP.
A package that runs on the user's computer	Click 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, its settings open. Its tools stay off until you enable them.

Section	Set
Tools	Turn on the tools agents may call. See Tool visibility.
Guardrails	Block or redact sensitive data in tool arguments and results. See Security Guardrails.
General > Access control	Limit the server to agents, smart groups or users. See Access Control.
Group & User Rules	Set different tools or guardrails for one group or user. See Group & User Rules.
Token saving	Compress tool results. See Token Saving.

Click Save settings before you close the drawer. For every section, see the Overview.

3. Connect your AI app

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

URL	Use it for
OneMCP, https://mcpgateway.quilr.ai/quilrone/mcp	Every MCP the user may use, through one connection. See OneMCP.
Quilr gateway URL from the server card, https://mcpgateway.quilr.ai/<slug>/mcp	One 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

Click Overall analytics, or Logs on a server card.

Tab	Check
Analytics	Tool calls, blocked calls, guardrail flags and tokens saved
Activity	Each tool call with its user, agent and guardrail outcome
Health	Rejected requests, access denials and upstream server errors

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

Related

• Overview - the MCP Gateway page, server card and workspace.
• Adding MCP Servers - every way to add a server.
• Agent Custom Instructions - configure clients to use the OneMCP discovery flow.