Cloudflare MCP server for AI agents

Cloudflare's Model Context Protocol (MCP) servers allow you to connect MCP clients (like Cursor or Claude) to your Cloudflare account, enabling natural language interactions with various Cloudflare services. These servers let you read configurations, process information, get suggestions, and implement changes across Cloudflare's ecosystem of application development, security, and performance tools.

Available MCP Servers

Cloudflare offers multiple specialized MCP servers:

Documentation server - Reference information on Cloudflare
Workers Bindings server - Build Workers applications with storage, AI, and compute primitives
Workers Builds server - Manage Cloudflare Workers Builds
Observability server - Debug applications with logs and analytics
Radar server - Access Internet traffic insights and URL scanning
Container server - Create sandbox development environments
Browser rendering server - Fetch web pages and take screenshots
Logpush server - Get Logpush job health summaries
AI Gateway server - Search logs and analyze prompts/responses
AutoRAG server - List and search documents
Audit Logs server - Query audit logs and generate reports
DNS Analytics server - Optimize DNS performance
Digital Experience Monitoring server - Monitor critical applications
Cloudflare One CASB server - Identify security misconfigurations
GraphQL server - Get analytics data using Cloudflare's GraphQL API

Connecting to MCP Servers

Using Clients with Native Support

If your MCP client directly supports remote MCP servers (like Cloudflare AI Playground), you can enter the server URL directly in the client interface.

Using Clients Without Native Support

For clients without built-in support, use the mcp-remote package to set up configuration:

{
	"mcpServers": {
		"cloudflare-observability": {
			"command": "npx",
			"args": ["mcp-remote", "https://observability.mcp.cloudflare.com/sse"]
		},
		"cloudflare-bindings": {
			"command": "npx",
			"args": ["mcp-remote", "https://bindings.mcp.cloudflare.com/sse"]
		}
	}
}

Using with OpenAI Responses API

To use Cloudflare's MCP servers with OpenAI's Responses API:

Create an API token in the Cloudflare dashboard at https://dash.cloudflare.com/profile/api-tokens
Ensure your token has the proper permissions required for the specific MCP server you want to use
Provide this API token to the OpenAI Responses API

Troubleshooting

Context Length Limitations

If you see a message like "Claude's response was interrupted...", the AI likely hit its context-length limit. This commonly happens with servers that trigger many chained tool calls, such as the observability server.

To reduce this issue:

Be specific and keep queries concise
Break requests into several smaller tool calls to keep responses short

Paid Features

Note that some features may require a paid Cloudflare Workers plan. Ensure your Cloudflare account has the necessary subscription level for the features you intend to use.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cloudflare-observability" '{"command":"npx","args":["mcp-remote","https://observability.mcp.cloudflare.com/sse"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

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.

Adding an MCP server to Cursor globally

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-observability": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://observability.mcp.cloudflare.com/sse"
            ]
        },
        "cloudflare-bindings": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://bindings.mcp.cloudflare.com/sse"
            ]
        }
    }
}

Adding an MCP server to a project

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.

How to use the MCP server

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.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cloudflare-observability": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://observability.mcp.cloudflare.com/sse"
            ]
        },
        "cloudflare-bindings": {
            "command": "npx",
            "args": [
                "mcp-remote",
                "https://bindings.mcp.cloudflare.com/sse"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect