Server profile

Cloudflare MCP Server

Cloudflare MCP Server is a collection of product-specific remote servers for Cloudflare accounts. It brings configuration, logs, analytics, documentation, and selected management workflows into compatible AI clients.

Server facts

Cloudflare MCP Server

Project

License
Apache-2.0

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
4,387
Last commit
Data as of

Tags

  • Cloudflare
  • Observability
  • Remote Mcp
  • Workers

Overview

Cloudflare MCP Server is a repository of specialized MCP services rather than a single tool endpoint. Its servers cover documentation, Workers bindings and builds, application observability, browser rendering, sandbox containers, and several security and analytics areas. Depending on the selected service, a client can inspect account configuration, analyze information, propose changes, or carry out supported changes. The browser service also handles fetching pages, Markdown conversion, and screenshots. This product-oriented layout lets users connect the particular Cloudflare domain they need instead of exposing an undifferentiated API surface.

The README contrasts these curated services with a separate Code Mode server, which targets broader API access through code execution. Here, each product service offers its own remote URL and supports Streamable HTTP, with deprecated SSE endpoints also available. Clients that understand remote MCP can connect directly; others can use the documented mcp-remote bridge. Integrations through the OpenAI Responses API require a Cloudflare API token carrying the permissions needed by the selected server. Some capabilities also depend on a paid Workers plan. For log-heavy investigations, the troubleshooting guidance recommends focused requests and smaller tool sequences because long chains can exhaust a client's context. The supplied README lists service purposes and endpoints but does not enumerate individual MCP tool identifiers.

Install & configure

Requirements

  • An MCP-compatible client
  • A Cloudflare account for account operations
  • npx when using the mcp-remote bridge
  • Appropriate API token permissions when using the OpenAI Responses API
Documented launch / install command
npx mcp-remote https://observability.mcp.cloudflare.com/mcp

This example selects the Observability server. Remote-capable clients can use its URL directly; the npx command is a compatibility bridge. Other product areas use separate URLs.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

A supported configuration example is not available for this client and transport. Check the client documentation for its connection flow; do not substitute an undocumented JSON format.

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "mcp-server-cloudflare": {
      "url": "https://observability.mcp.cloudflare.com/mcp"
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcp-server-cloudflare": {
      "type": "http",
      "url": "https://observability.mcp.cloudflare.com/mcp"
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "mcp-server-cloudflare": {
      "serverUrl": "https://observability.mcp.cloudflare.com/mcp"
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcp-server-cloudflare": {
      "type": "http",
      "url": "https://observability.mcp.cloudflare.com/mcp"
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Investigate Workers logs and application analytics.
  • Consult current Cloudflare reference documentation.
  • Work with Workers storage, AI, and compute bindings.
  • Review account audit logs or security misconfiguration information.
  • Fetch pages and screenshots with the browser rendering service.

Strengths

  • Provides distinct endpoints for specific Cloudflare product areas.
  • Supports direct remote access and a bridge for local-only clients.
  • Covers development, security, and analytics workflows.

Limitations

  • Some capabilities require a paid Cloudflare Workers plan.
  • Long tool chains can exceed client context limits.
  • SSE remains available but is deprecated.

Frequently asked questions

No. This repository contains product-specific services. The README points broad code-execution workflows to a separate Code Mode repository.

The services expose Streamable HTTP at /mcp. SSE at /sse is documented as deprecated.

Yes. The README shows npx mcp-remote as a bridge to the hosted endpoints.

Not necessarily. The README notes that some features may need a paid Cloudflare Workers plan.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

EdgeOne Makers MCP

Cloud & DevOps

EdgeOne Makers MCP publishes full-stack projects and gives users a public address for the result. A separate hosted connection handles lightweight HTML previews without running the package locally.

Open Source MCP Servers for AWS

Cloud & DevOps

This AWS Labs repository collects specialized MCP servers for AWS documentation, cloud development, and operational workflows. It is a suite to choose from rather than one server exposing a single fixed tool catalog.

Terraform MCP Server

Cloud & DevOps

Connect MCP assistants to Terraform Registry data and HCP Terraform or Terraform Enterprise. It supports infrastructure research, private registry access, and workspace operations with selectable tools and deployment transports.

Kubernetes MCP Server

Cloud & DevOps

Give MCP assistants direct Kubernetes and OpenShift API access. The native Go server supports resource operations, pod diagnostics, Helm releases, and Tekton tasks, with configurable restrictions and multi-cluster support.

MCP Server Kubernetes

Cloud & DevOps

MCP Server Kubernetes lets assistants inspect and manage clusters through kubectl-oriented tools. It covers resources, logs, rollouts, Helm releases, port forwarding, and diagnostics using an existing Kubernetes context.

kubectl-mcp-server

Cloud & DevOps

kubectl-mcp-server connects assistants to Kubernetes inspection and management workflows. It covers pod diagnostics, deployments, networking, Helm, security reviews, resource analysis, and optional dashboards.

Cloud Run MCP Server

Cloud & DevOps

Cloud Run MCP Server connects agents to application deployment and service inspection on Google Cloud Run. It offers a local credential-based setup, Gemini CLI integration, and authenticated remote operation with specific limits.