Cloudflare
The Cloudflare MCP Server repository is a collection of official MCP servers that let you manage your Cloudflare account and services from your favorite MCP client, like Cursor or Claude.
MCP Servers Included
- 📚 Documentation: Get up-to-date reference information on Cloudflare.
- 🛠️ Workers Bindings: Build Workers applications with storage, AI, and compute primitives.
- 🏗️ Workers Builds: Get insights and manage your Cloudflare Workers Builds.
- 📊 Observability: Debug and get insight into your application’s logs and analytics.
- 🌐 Radar: Get global Internet traffic insights, trends, URL scans, and other utilities.
- 📦 Container: Spin up a sandbox development environment.
- 🖥️ Browser Rendering: Fetch web pages, convert them to markdown, and take screenshots.
- 📜 Logpush: Get quick summaries for Logpush job health.
- 🤖 AI Gateway: Search your logs and get details about prompts and responses.
- 📄 AutoRAG: List and search documents on your AutoRAGs.
- 🛡️ Audit Logs: Query audit logs and generate reports for review.
- 📈 DNS Analytics: Optimize DNS performance and debug issues based on your current setup.
- 💻 Digital Experience Monitoring: Get quick insight on critical applications for your organization.
- 🔐 Cloudflare One CASB: Quickly identify any security misconfigurations for SaaS applications to safeguard users and data.
- ✨ GraphQL: Get analytics data using Cloudflare’s GraphQL API.
How to Use It
The Cloudflare MCP Server collection operates through remote server endpoints that integrate with MCP-compatible clients. Each specialized server handles specific Cloudflare service domains and requires proper authentication credentials.
Authentication Setup
Create API tokens in the Cloudflare dashboard with appropriate permissions for each service you plan to access. Different servers require different permission scopes. For example, the Browser Rendering server needs specific rendering permissions, while the Observability server requires log and analytics access.
Client Configuration for Remote Access
MCP clients with native remote server support can connect directly using the provided server URLs. For clients requiring configuration files, install the mcp-remote package and configure your client’s MCP server settings:
{
"mcpServers": {
"cloudflare-docs": {
"command": "npx",
"args": ["mcp-remote", "https://docs.mcp.cloudflare.com/sse"]
},
"cloudflare-workers": {
"command": "npx",
"args": ["mcp-remote", "https://bindings.mcp.cloudflare.com/sse"]
},
"cloudflare-observability": {
"command": "npx",
"args": ["mcp-remote", "https://observability.mcp.cloudflare.com/sse"]
}
}
}Integration with OpenAI Responses API
Configure OpenAI’s Responses API to work with Cloudflare MCP servers by providing API tokens with the required scopes. Each server documents its specific permission requirements in the respective configuration guides.
FAQs
Q: Can I use multiple Cloudflare MCP servers simultaneously in one client?
A: Yes, you can configure multiple servers in your MCP client. Each server operates independently and handles requests for its specific service domain. Configure each server with its respective endpoint URL and ensure your API tokens have the necessary permissions for all services you plan to access.
Q: What happens when Claude’s response gets interrupted during complex queries?
A: Response interruption typically occurs when queries trigger multiple tool calls that exceed context limits. Break complex requests into smaller, focused queries targeting specific services or data ranges. This approach reduces response length and prevents mid-conversation truncation.
Q: Do I need paid Cloudflare subscriptions to use all server features?
A: Some functionality requires paid Cloudflare plans, particularly advanced Workers features, detailed analytics, and enterprise security tools. Check your account’s subscription level against the specific features you intend to use. Basic functionality often works with free tier accounts.
Q: How do I troubleshoot authentication failures with specific servers?
A: Verify that your API tokens include the correct permission scopes for each server. Different servers require different combinations of account, zone, and service-specific permissions. Review the permission requirements in each server’s documentation and regenerate tokens with appropriate scopes if needed.
Latest MCP Servers
CVE
WebMCP
webmcp is an MCP server that connects MCP clients to web search, page fetching, and local LLM-based extraction. It’s ideal…
Google Meta Ads GA4
Featured MCP Servers
Notion
Claude Peers
Excalidraw
FAQs
Q: What exactly is the Model Context Protocol (MCP)?
A: MCP is an open standard, like a common language, that lets AI applications (clients) and external data sources or tools (servers) talk to each other. It helps AI models get the context (data, instructions, tools) they need from outside systems to give more accurate and relevant responses. Think of it as a universal adapter for AI connections.
Q: How is MCP different from OpenAI's function calling or plugins?
A: While OpenAI's tools allow models to use specific external functions, MCP is a broader, open standard. It covers not just tool use, but also providing structured data (Resources) and instruction templates (Prompts) as context. Being an open standard means it's not tied to one company's models or platform. OpenAI has even started adopting MCP in its Agents SDK.
Q: Can I use MCP with frameworks like LangChain?
A: Yes, MCP is designed to complement frameworks like LangChain or LlamaIndex. Instead of relying solely on custom connectors within these frameworks, you can use MCP as a standardized bridge to connect to various tools and data sources. There's potential for interoperability, like converting MCP tools into LangChain tools.
Q: Why was MCP created? What problem does it solve?
A: It was created because large language models often lack real-time information and connecting them to external data/tools required custom, complex integrations for each pair. MCP solves this by providing a standard way to connect, reducing development time, complexity, and cost, and enabling better interoperability between different AI models and tools.
Q: Is MCP secure? What are the main risks?
A: Security is a major consideration. While MCP includes principles like user consent and control, risks exist. These include potential server compromises leading to token theft, indirect prompt injection attacks, excessive permissions, context data leakage, session hijacking, and vulnerabilities in server implementations. Implementing robust security measures like OAuth 2.1, TLS, strict permissions, and monitoring is crucial.
Q: Who is behind MCP?
A: MCP was initially developed and open-sourced by Anthropic. However, it's an open standard with active contributions from the community, including companies like Microsoft and VMware Tanzu who maintain official SDKs.
