Skip to main content

Cloudflare Workers Bindings

Connect AI tools to Cloudflare Workers Bindings to build Workers applications with storage, AI, and compute primitives. The Cloudflare Workers Bindings MCP server gives AI assistants programmatic access to Workers bindings (KV, D1, R2, AI, etc.) through the Model Context Protocol (MCP).

1. Overview​

Cloudflare Workers Bindings is a remote, vendor-hosted MCP server provided by Cloudflare. You connect to it from Cequence AI Gateway; the server uses Streamable HTTP (the standard transport for remote MCP per Cloudflare’s MCP docs).

  • Server URL: https://bindings.mcp.cloudflare.com/mcp
  • Transport: HTTP (Streamable HTTP)
  • Hosted by: Cloudflare

2. Supported authentication types​

TypeSupportedNotes
OAuth 2.0YesRequired. Uses Dynamic Client Registration (DCR); sign in with your Cloudflare account.
API keyNoNot used for this remote MCP server.

When you add Cloudflare Workers Bindings in Cequence AI Gateway, authentication is handled via OAuth 2.0 with Dynamic Client Registration. You sign in with your Cloudflare account and grant access during the gateway flow.

3. What can you do with this MCP server​

With the Cloudflare Workers Bindings MCP server, you can:

  • Work with storage and compute — Interact with Workers bindings for storage (e.g. KV, R2, D1), AI, and compute from your AI client.
  • Build and manage Workers — Use natural language to create or manage bindings and Worker-related resources.
  • List and create KV namespaces — List all KV namespaces in your account and create new ones; manage keys and values.
  • Use D1 and R2 — Read from or create D1 databases and R2 buckets; implement storage in your Workers application from natural language.
  • Read existing resources — Read existing bindings and resources from your account so generated code can use them.
  • Create fresh resources — Create new namespaces, databases, or buckets and get the details to implement in your application (e.g. with the Workers base prompt for full-stack generation).

4. Prerequisites​

Before adding Cloudflare Workers Bindings in Cequence AI Gateway, ensure you have:

  • Access to Cequence AI Gateway (e.g. beta.aigateway.cequence.ai)
  • A Cloudflare account with Workers and the bindings you want to use
  • A modern browser to complete the OAuth authorization flow
  • For OAuth authentication: an auth app with client credentials (client ID and client secret) in your Cloudflare (vendor) account, unless the server supports Dynamic Client Registration (DCR).

5. Example workflows​

  • “List my KV namespaces and show the last 5 keys in [namespace].”
  • “Create a new D1 database and return the database ID.”
  • “Run a query against my D1 database [name].”

6. Connecting MCP server from Cequence AI Gateway​

  1. Log in to Cequence AI Gateway.
  2. Choose your tenant.
  3. Go to App catalogue.
  4. Filter by Remote MCP server.
  5. Search for Cloudflare Workers Bindings and then select it.
  6. Click Create MCP server.
  7. Choose auth method. If OAuth, you need an auth app with client credentials in your vendor account (see Prerequisites).
  8. Complete the setup as prompted, select tools, and deploy.

Use the generated MCP server URL in your client as described in the Client Configuration docs. For detailed UI steps and screenshots, see Create a third-party MCP Server.

7. Additional information​