This MCP server provides a Model Context Protocol implementation that connects to Cloudflare AI Gateway, allowing you to access various AI Gateway tools through any compatible MCP client. It comes with built-in Cloudflare OAuth authentication to securely access your account resources.
The server currently provides these Cloudflare AI Gateway tools:
Tool | Description |
---|---|
list_gateways |
Lists all AI Gateways associated with the account, supporting pagination for easy navigation. |
list_logs |
Retrieves logs for a specified gateway, offering filters such as date ranges, feedback scores, success status, model, and provider. |
get_log_details |
Fetches detailed information about a specific log identified by its log ID within a gateway. |
get_log_request_body |
Retrieves the request body associated with a specific log in a gateway. |
get_log_response_body |
Retrieves the response body associated with a specific log in a gateway. |
Note: To use these tools, you must have an active account set. If needed, use accounts_list
to list your accounts and set_active_account
to set one as active.
If your MCP client directly supports remote MCP servers, simply enter the server URL:
https://ai-gateway.mcp.cloudflare.com
This works with clients like Cloudflare AI Playground.
If your client doesn't yet support remote MCP servers directly, follow these steps:
npm install -g mcp-remote
{
"mcpServers": {
"cloudflare": {
"command": "npx",
"args": ["mcp-remote", "https://ai-gateway.mcp.cloudflare.com/sse"]
}
}
}
Here are some example prompts you can use with the MCP server:
List all my AI Gateways.
Show logs for gateway 'gateway-001' between January 1, 2023, and January 31, 2023.
Fetch the latest errors from gateway-001 and debug what might have happened wrongly
The server will intelligently interpret these natural language requests and execute the appropriate tool calls to retrieve the requested information.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "cloudflare" '{"command":"npx","args":["mcp-remote","https://ai-gateway.mcp.cloudflare.com/sse"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cloudflare": {
"command": "npx",
"args": [
"mcp-remote",
"https://ai-gateway.mcp.cloudflare.com/sse"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"cloudflare": {
"command": "npx",
"args": [
"mcp-remote",
"https://ai-gateway.mcp.cloudflare.com/sse"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect