Cloudflare MCP Server

Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, you can find several MCP servers allowing you to connect to Cloudflare's service from an MCP client (e.g. Cursor, Claude) and use natural language to accomplish tasks through your Cloudflare account.

These MCP servers allow your MCP Client to read configurations from your account, process information, make suggestions based on data, and even make those suggested changes for you. All of these actions can happen across Cloudflare's many services including application development, security and performance.

They support both the streamable-http transport via /mcp and the sse transport (deprecated) via /sse.

The following servers are included in this repository:

Which Cloudflare MCP server should you use?

Cloudflare provides two categories of MCP servers:

• Code Mode server (mcp.cloudflare.com) in cloudflare/mcp: best when you want broad access across Cloudflare's APIs through code execution.
• Domain-specific servers (*.mcp.cloudflare.com) in this repository: best when you want curated, typed tools for a specific Cloudflare product area.

When should you use each?

Use the Code Mode server when:

• you need broad API coverage across many Cloudflare products
• you prefer a smaller set of general-purpose tools
• your workflow is better served by code execution

Use the domain-specific servers in this repository when:

• you want purpose-built tools for a specific product area
• you want more guided, typed interactions
• you are working primarily within one Cloudflare domain such as observability, bindings, Radar, or Browser Rendering

Learn more about the Code Mode server here: cloudflare/mcp.

Access the remote MCP server from any MCP client

If your MCP client has first class support for remote MCP servers, the client will provide a way to accept the server URL directly within its interface (e.g. Cloudflare AI Playground)

If your client does not yet support remote MCP servers, you will need to set up its respective configuration file using mcp-remote (https://www.npmjs.com/package/mcp-remote) to specify which servers your client can access.

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

Using Cloudflare's MCP servers from the OpenAI Responses API

To use one of Cloudflare's MCP servers with OpenAI's responses API, you will need to provide the Responses API with an API token that has the scopes (permissions) required for that particular MCP server.

For example, to use the Browser Rendering MCP server with OpenAI, create an API token in the Cloudflare dashboard here, with the following permissions:

Need access to more Cloudflare tools?

We're continuing to add more functionality to this remote MCP server repo. If you'd like to leave feedback, file a bug or provide a feature request, please open an issue on this repository

Troubleshooting

"Claude's response was interrupted ... "

If you see this message, Claude likely hit its context-length limit and stopped mid-reply. This happens most often on servers that trigger many chained tool calls such as the observability server.

To reduce the chance of running in to this issue:

• Try to be specific, keep your queries concise.
• If a single request calls multiple tools, try to to break it into several smaller tool calls to keep the responses short.

Paid Features

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.

Contributing

Interested in contributing, and running this server locally? See CONTRIBUTING.md to get started.