Skip to main content
You can launch a guided setup directly from the Spur app. Go to Integrations → MCP and click Setup to open a step-by-step modal for your platform.

Server details

Use these settings for any client that supports remote Model Context Protocol (MCP) servers: When you connect for the first time, your browser opens so that you can authorize access to your Spur account.

Cursor

Click the button to install Spur directly in Cursor, or copy the deep link below and paste it into your browser address bar. Install MCP Server

Claude Code

Run this command in your terminal:
Open Claude Code, run /mcp, and complete the OAuth flow.

Codex

Codex CLI and the Codex IDE extension share the same MCP configuration. Run these commands in your terminal:
Complete the OAuth flow in your browser. Run codex mcp list or /mcp in a Codex session to verify the connection.

Claude Desktop and Claude.ai

1

Open Connectors settings

Go to Settings and navigate to the Connectors tab. Claude.ai users can go directly to claude.ai/settings/connectors.
Connectors tab in Claude settings
2

Add a custom connector

Click Add custom connector.
Add custom connector button
3

Enter the server URL

Set the URL to https://app.spurtest.com/api/mcp.
Add custom connector modal with Spur MCP URL
4

Authenticate

Complete the OAuth authorization flow. Your browser opens so that you can authorize access to your Spur account.

GitHub Copilot in VS Code

1

Open the MCP Server section

Make sure the GitHub Copilot extension is installed. Open the Copilot panel and navigate to the MCP Servers section.
GitHub Copilot extension with MCP Server section
2

Add a new server

Open the Command Palette (Cmd+Shift+P on Mac, Ctrl+Shift+P on Windows/Linux) and type MCP: Add Server.
MCP: Add Server in the Command Palette
3

Select HTTP transport

Select HTTP (HTTP or Server-Sent Events).
Selecting HTTP transport type
4

Enter the server URL

Set the URL to https://app.spurtest.com/api/mcp.
Entering the Spur MCP server URL
5

Name the server

Enter a server name. Spur is recommended.
Naming the MCP server
6

Authenticate

Complete the OAuth authorization flow. Your browser opens so that you can authorize access to your Spur account.

ChatGPT

1

Open settings

Select Settings from the drop-down menu.
Open the ChatGPT settings menu
2

Navigate to Advanced Settings

Click Advanced Settings under the Apps tab.
Advanced Settings under the Apps tab
3

Enable developer mode

Toggle Developer mode on.
Enable developer mode
4

Create a new app

Click Create app.
Create a new app
5

Enter the MCP URL

Set the URL to https://app.spurtest.com/api/mcp.
Enter the Spur MCP URL
6

Authorize the Spur app

Complete the OAuth authorization flow.
Authorize the Spur app
7

Confirm the new app

Verify the app was created successfully.
Confirm the new app
8

Select Spur in Connectors

Select Spur from the Connectors list.
Choose Spur in the Connectors list
9

Start prompting

You’re all set. Start using Spur through ChatGPT.
Prompting ChatGPT with Spur

Gemini CLI

Run this command to add Spur to your user configuration:
Start Gemini CLI, run /mcp auth spur, and complete the OAuth flow in your browser.

Windsurf

1

Open the MCP configuration

In Cascade, click MCPs, or go to Windsurf Settings → Cascade → MCP Servers. Open the raw mcp_config.json file.
2

Add Spur

Add spur to the existing mcpServers object:
3

Authenticate

Save the file, connect to Spur, and complete the OAuth flow in your browser.

Zed

1

Open your settings file

Run zed: open settings file from the command palette.
2

Add Spur

Add spur to the existing context_servers object:
3

Authenticate

Save the file. Zed prompts you to complete the OAuth flow in your browser.

Other MCP clients

If your client supports remote Streamable HTTP servers and OAuth, use the server details above. If it only supports local command-based servers, use this command through its MCP configuration:

Verify the connection

Open your client’s MCP server list and confirm that Spur is connected and its tools are available.