Skip to main content

Getting Started

The Cequence AI Gateway enables you to create MCP servers in two ways:

  1. From OpenAPI Specifications: Upload an OpenAPI spec to create an MCP server that wraps your REST API
  2. From Remote MCP Servers: Connect to existing MCP servers and proxy their tools through the AI Gateway

Both approaches let you add authentication, security policies, and monitoring to your MCP tools.

Once you have the MCP server defined, you can connect the server to your LLM tool of choice. The Cequence AI Gateway directly supports integration with Claude, Cursor, and the Windsurf IDE, and you can also manually integrate with any other LLM you're using.

Quick Start Options​

Option 1: Create from OpenAPI Specification​

Define an 'app' within the App Catalog. In this context, an app is just a container for an API specification that lets you specify some tags and other metadata for organization. You can launch the MCP server creation flow directly and upload the API specification from there.

Option 2: Connect Remote MCP Server​

Connect to an existing MCP server by providing its URL and authentication credentials. The AI Gateway will discover available tools and create a proxy MCP server. See Adding a Remote MCP Server below.

Creating an App (OpenAPI Specification)​

This section covers creating an MCP server from an OpenAPI specification.

Once you've logged in to the Cequence AI Gateway, click Apps. Several apps are already available, but for this example, we'll make a new app from the start. Click the +Custom App button in the top right.

A picture of an interface element showing a button labeled '+Custom App' at the top rightA picture of an interface element showing a button labeled '+Custom App' at the top right

The Add Custom App dialogue box appears. On the right side of the dialogue box, there's a space where you can upload an API specification, either by dragging the file to that area or by clicking Browse Files to navigate your file system. The file must be in the OpenAPI format.

All fields other than the API specification and app name are optional. The description, primary category, app family, and secondary category are meant to help you organize your apps and quickly find a specific app.

Click Create App to return to the App Catalog. You're ready to start the MCP server that provides the new app's functionality.

Create the MCP Server from an App​

Find your new app in the App Catalog. You can click the paired arrows icon to show the sorting options. Click Newest to Oldest to show the app you just created at the top of the App Catalog.

Click your new app to show a summary of the API specification associated with that app. Click Create MCP Server to start. The Create MCP Server wizard appears.

Excerpt of a multi-step timeline showing two steps, App Configuration and MCP Server Setup. App Configuration is highlighted.Excerpt of a multi-step timeline showing two steps, App Configuration and MCP Server Setup. App Configuration is highlighted.

App Configuration

Choose an option from the Base URL drop-down. The Cequence AI Gateway derives these URLs from the API specification you uploaded earlier. In the API Tools for AI Agents pane, you can type a string in the search field to filter the list of endpoints, or select a method from the Filter by method: list. Select a set of endpoints for the MCP server and click Next.

Excerpt of a multi-step timeline showing two steps, App Configuration and MCP Server Setup. App Configuration is marked completed and MCP Server Setup is highlighted.Excerpt of a multi-step timeline showing two steps, App Configuration and MCP Server Setup. App Configuration is marked completed and MCP Server Setup is highlighted.

MCP Server Setup

At this step, you can change the server name and description, as well as set the log level. Production Mode produces terser logs, while Non-Production Mode creates more verbose logs with additional information you might find useful for debugging or tracing specific behavior. Click Next to advance.

Excerpt of a multi-step timeline showing two steps, MCP Server Setup and Authentication. MCP Server Setup is marked completed and Authentication is highlighted.Excerpt of a multi-step timeline showing two steps, MCP Server Setup and Authentication. MCP Server Setup is marked completed and Authentication is highlighted.

Authentication

Specify what kind of authentication you'll use for this MCP server.

Passthrough: The MCP server forwards any existing credentials directly to the service, making no changes. If you use API keys, Basic Auth, custom headers, or no authentication at all, select Passthrough.

OAuth 2.0 Authorization: User-delegated access requiring browser-based login. You'll need:

  • Authorization URL
  • Token URL
  • Client ID
  • Client Secret
  • Optionally, scopes

OAuth 2.0 Client Credentials: Service-to-service authentication without user interaction. You'll need:

  • Token URL
  • Client ID
  • Client Secret
  • Optionally, scopes

Once you've selected the authentication type and provided any needed items, click Next to advance.

Excerpt of a multi-step timeline showing two steps, Authentication and Review. Authentication is marked completed and Review is highlighted.Excerpt of a multi-step timeline showing two steps, Authentication and Review. Authentication is marked completed and Review is highlighted.

Review

Look over a summary of your MCP server configuration and click Create & Deploy when ready. Deploying takes a few minutes. Watch the Dashboard for the Deploying... message to clear.

Adding a Remote MCP Server​

If you have an existing MCP server running elsewhere, you can connect it to the AI Gateway to add authentication, monitoring, and security controls.

Step 1: Navigate to App Catalog​

From the Cequence AI Gateway dashboard, click Apps in the sidebar, then click + Remote MCP in the top right corner.

Step 2: Configure Server URL​

In the Add Remote MCP Server dialog:

  1. MCP Server URL: Enter the URL of your remote MCP server (e.g., https://example.com/mcp)
  2. Authentication Method: Choose from the dropdown:
    • Auto-detect (Recommended): Automatically detects if the server supports OAuth with Dynamic Client Registration (DCR) or requires no authentication
    • OAuth 2.0 (Authorization Code): User authorization with manual OAuth endpoints - requires browser-based user login
    • OAuth 2.0 (Client Credentials): Service-to-service authentication without user interaction - ideal for machine-to-machine communication
    • No Authentication: Server does not require authentication
    • Basic Authentication: Username and password
    • Bearer Token: Static bearer token
    • API Key: Custom header with API key

Step 3: Authentication Configuration​

The system automatically:

  • Attempts connection without auth
  • If 401/403 received, checks for OAuth support via .well-known/oauth-authorization-server
  • Performs Dynamic Client Registration (DCR) if available
  • Initiates OAuth flow automatically

No manual configuration required.

OAuth 2.0 (Authorization Code)​

For servers requiring user authorization:

Required fields:

  • Authorization URL: OAuth authorization endpoint (e.g., https://auth.example.com/oauth/authorize)
  • Token URL: OAuth token endpoint (e.g., https://auth.example.com/oauth/token)
  • Client ID: Your OAuth client identifier
  • Client Secret: Your OAuth client secret
  • Scopes (optional): Space or comma-separated list of OAuth scopes

Flow:

  1. Click Test Connection
  2. System opens OAuth provider in new browser window
  3. You log in and authorize access
  4. System redirects back and discovers available tools
  5. Review and create the MCP server

OAuth 2.0 (Client Credentials)​

For service-to-service authentication without user interaction:

Required fields:

  • Token URL: OAuth token endpoint (e.g., https://auth.example.com/oauth/token)
  • Client ID: Your OAuth client identifier
  • Client Secret: Your OAuth client secret
  • Scopes (optional): Comma-separated list of OAuth scopes

Flow:

  1. Click Test Connection
  2. System exchanges credentials for access token directly
  3. No browser redirect - tools are discovered immediately
  4. Review and create the MCP server

When to use:

  • Machine-to-machine authentication
  • Automated/scheduled operations
  • No user context required
  • Background services

Basic Authentication​

Enter username and password. Credentials are securely transmitted during discovery.

Bearer Token​

Enter a static bearer token. It will be sent as: Authorization: Bearer <token>

API Key​

Enter API key and specify the header name (default: X-API-Key).

Custom Headers​

For all authentication methods, you can optionally add custom HTTP headers to the connection. This is useful for:

  • API versioning headers (e.g., Accept: application/vnd.api+json)
  • Request tracing headers (e.g., X-Request-ID)
  • Custom authentication headers required by the remote server
  • Debug or feature flags

Click Show Custom Headers to expand the section and add header key-value pairs.

OAuth Callback URL (Authorization Code Flow Only)

When using OAuth 2.0 (Authorization Code) and manually configuring OAuth with your provider, use this callback URL:

https://connect.aigateway.cequence.ai/oauth/callback

This URL is automatically registered when using Auto-detect with Dynamic Client Registration (DCR).

Step 4: Test Connection​

Click Test Connection to discover available tools from the remote MCP server. The system will:

  • Connect to the MCP server using your authentication
  • Discover all available tools
  • Display tool names and descriptions

Step 5: Customize and Create​

Optional customization:

  • Name: Custom name for the MCP server (defaults to remote server's name)
  • Description: Custom description
  • Categories: Primary category, app family, and secondary categories for organization
  • Labels: Tags for easier searching

Click Next to create the MCP server in your catalog.

Step 6: Create Gateway​

After adding the remote MCP server to your catalog, you can create a gateway:

  1. Click the remote MCP server in the App Catalog
  2. Click Create MCP Server
  3. Follow the wizard to configure deployment and authentication for the gateway

Integrate with your LLM agent​

Once your MCP server is deployed and running, go to the Cequence AI Gateway dashboard and click the tile for your server to manage integrations. Click Create Agent Integration to start.

The Cequence AI Gateway supports quick integrations with the following agents.

  • Claude AI
  • Cursor AI
  • Windsurf IDE

Click Create Agent Integration to bring up the Easy Integration Setup pane. Choose the tab for the agent you're integrating with and click the copy icon in the Quick Setup (NPX) tab. The command-line instruction to integrate the MCP server with your AI agent is in your clipboard. Paste the command to a terminal window and run the command. A confirmation message at your terminal indicates that you're ready to test the integration.

Testing the integration​

The next time you authenticate to the agent, you will need to provide your authentication credentials if you configured the MCP server to use OAuth 2.0. Run your AI agent and select the list of tools. This varies based on your agent. Using Claude as an example, the tools control is at the bottom of the text field, next to the Upload a file icon. The tools are enabled by default, but you can disable them by selecting the toggles on the list. To use the tool, refer to the tool in your prompt. For example, if your MCP server provides a tool based on a customer details endpoint, you can use Show me the customer details for user ID 12345 as the prompt, and your AI agent makes the proper request to the customer details endpoint and reports back.