Skip to main content

Connect MCP Express with OAuth

Learn how to connect your AI tool to an MCP Express server using MCP OAuth.

Once connected, your AI tool will have access to every tool you've built and published on your authorized server.

Prerequisites​

Before you begin, ensure you have:

  • An active MCP Express account with at least one server configured
  • An AI tool that supports remote MCP servers
tip

Not sure if your tool supports MCP? Look for Model Context Protocol or MCP server support in its documentation.

Step 1: Configure your AI tool​

Choose your AI client and follow the setup instructions below.

Claude Code​

Run the following command:

claude mcp add --transport http mcp-express https://api.mcp-express.com/gateway/mcp

Then run: /mcp and complete the authorization flow when prompted.

info

Need more details on setup, commands, and MCP behavior in Claude Code? View Claude Code docs

Cursor​

  1. Open Cursor Settings → MCP → Add new global MCP server
  2. Paste:
{
  "mcpServers": {
    "mcp-express": {
      "url": "https://api.mcp-express.com/gateway/mcp"
    }
  }
}
  1. Save and restart Cursor
  2. Trigger any MCP tool and complete authorization
tip

You can share this configuration with your team by adding a .cursor/mcp.json file to your project’s root directory.

info

Learn how Cursor integrates with MCP servers and manages context. View Cursor MCP docs

VS Code​

  1. Create .vscode/mcp.json:
{
  "servers": {
    "mcp-express": {
      "type": "http",
      "url": "https://api.mcp-express.com/gateway/mcp"
    }
  }
}
  1. Open Command Palette (Ctrl+Shift+P)
  2. Run MCP: List Servers
  3. Start MCP Express and complete authorization
tip

Use MCP: Open User Configuration to apply this configuration across all workspaces.

info

Explore how MCP servers work within VS Code and how to manage them effectively. View VS Code MCP docs

Claude Desktop​

  1. Open Settings → Connectors
  2. Click Add Connector
  3. Enter:
https://api.mcp-express.com/gateway/mcp
  1. Complete the authorization flow
info

Read more about configuring connectors and using MCP servers in Claude Desktop. View Claude Desktop docs

Windsurf​

  1. Open Settings (Cmd + ,)
  2. Search for MCP
  3. Open mcp_config.json
  4. Add:
{
  "mcpServers": {
    "mcp-express": {
      "serverUrl": "https://api.mcp-express.com/gateway/mcp"
    }
  }
}
  1. Save and restart Windsurf
  2. Complete authorization when prompted
info

Understand how MCP configuration works in Windsurf and how to extend it. View Windsurf MCP docs

Codex​

  1. Open your Codex configuration file:
~/.codex/config.toml
  1. Add the MCP server configuration:
[mcp_servers.mcp-express]
url = "https://api.mcp-express.com/gateway/mcp"
  1. Run the following command:
codex mcp login mcp-express
  1. Complete authorization
tip

Use a .codex/config.toml file in your project root to share configuration across your team.

info

For deeper guidance on authentication, configuration, and MCP usage in Codex: View Codex MCP docs

Other tools​

If your AI tool supports MCP, connect using:

https://api.mcp-express.com/gateway/mcp

Most tools accept either a direct URL or a JSON configuration.

Step 2: Authorize access​

Once configured, your AI tool will open a browser window.

MCP Express Authorization Screen

  1. Select your Authentication Server
  2. Click Authorize
  3. You will be redirected back to your AI tool

Available tools​

After authorization, your AI assistant will have access to all tools published on your server.

To view available tools, ask:

What tools do you have access to? Use MCP.

Your AI assistant will list all available tools on your authorized server, along with a brief description of each.

If a tool is missing, ensure you are connected to the correct server and check your MCP Express servers

Troubleshooting​

Authorization issues
  • Make sure you complete the OAuth flow when prompted
  • Try disconnecting and reconnecting the integration
  • Look for a “Clear authentication” or “Disconnect” option in your AI tool’s MCP settings
No tools or changes not reflecting
  • Ensure you are connected to the correct MCP server
  • Verify the server contains the expected tools
  • Reconnect to refresh the session or trigger a fresh MCP request in your AI tool
No tools are showing after connecting
  • Ensure you are connected to the correct MCP server
  • Verify the server you selected contains the expected tools
  • Reconnect to refresh the session

For any issues not covered above, or if you need further assistance, please contact our support team: MCP Express Support

Unsupported Tools​

If your AI client does not support MCP OAuth, it is recommended to use Client Credentials as an alternative. Refer to the MCP Express Client Credentials Guide for detailed instructions on securely configuring access to all tools on your authorized server.