# Cloudflare Workers Bindings (MCP Server)

> Manage Workers, KV, R2, D1 and Hyperdrive resources

- Type: MCP server
- Publisher: Cloudflare (official)
- Categories: DevOps & Cloud, Development
- Website: https://github.com/cloudflare/mcp-server-cloudflare/tree/main/apps/workers-bindings
- Source: https://github.com/cloudflare/mcp-server-cloudflare
- Transport: streamable-http
- Server URL: https://bindings.mcp.cloudflare.com/mcp
- Sign-in: oauth
- GitHub stars: 4300
- Listed: 2025-05-01

## About

Cloudflare's remote Workers Bindings MCP server lets agents list and manage Workers storage and compute primitives, including KV namespaces, R2 buckets, D1 databases and Hyperdrive configs. It can also read Worker code and run D1 queries. Authentication is via Cloudflare OAuth.

## Install

1. **Connect it in ChatGPT** Turn on Developer mode in ChatGPT (Settings → Security and login), open Plugins, select + and paste https://bindings.mcp.cloudflare.com/mcp as the MCP server URL, then sign in with OAuth. Add it to a chat from the composer's tools menu.

2. **Or add it to Codex or the API**

   Codex CLI:

   ```bash
   codex mcp add cloudflare-workers-bindings --url https://bindings.mcp.cloudflare.com/mcp
   codex mcp login cloudflare-workers-bindings
   ```

   config.toml:

   ```toml
   [mcp_servers.cloudflare-workers-bindings]
   url = "https://bindings.mcp.cloudflare.com/mcp"
   ```

   Responses API:

   ```python
   import os
   from openai import OpenAI
   
   client = OpenAI()
   
   response = client.responses.create(
       model="gpt-6-astra",
       tools=[{
           "type": "mcp",
           "server_label": "cloudflare_workers_bindings",
           "server_url": "https://bindings.mcp.cloudflare.com/mcp",
           "authorization": os.environ["CLOUDFLARE_WORKERS_BINDINGS_API_KEY"],
           "require_approval": "never",
       }],
       input="Create a KV namespace named sessions",
   )
   print(response.output_text)
   ```

## Tools

- `workers_list`
- `workers_get_worker`
- `workers_get_worker_code`
- `kv_namespaces_list`
- `kv_namespace_create`
- `r2_buckets_list`
- `r2_bucket_create`
- `d1_databases_list`
- `d1_database_create`
- `d1_database_query`
- `hyperdrive_configs_list`
- `hyperdrive_config_create`

## Example prompts

- "Create a KV namespace named sessions"
- "List my D1 databases and run SELECT count(*) FROM users on prod-db"
- "Show me the code for my api-gateway Worker"
- "Create an R2 bucket for user uploads"

## Also available as

- plugin: [Cloudflare](https://chatgptplugins.directory/plugins/cloudflare.md)
- app: [Cloudflare](https://chatgptplugins.directory/apps/cloudflare.md)

## Related

- [Chrome DevTools MCP](https://chatgptplugins.directory/mcp/chrome-devtools.md): Let coding agents control and debug a live Chrome browser
- [Playwright MCP](https://chatgptplugins.directory/mcp/playwright.md): Browser automation for agents via Playwright accessibility snapshots
- [GitHub](https://chatgptplugins.directory/mcp/github.md): Manage repos, issues, pull requests and Actions from your AI agent
- [Context7](https://chatgptplugins.directory/mcp/context7.md): Pull up-to-date, version-specific library docs into your coding agent
- [Supabase](https://chatgptplugins.directory/mcp/supabase.md): Manage Supabase databases, migrations, edge functions and logs
- [Stripe](https://chatgptplugins.directory/mcp/stripe.md): Query and act on your Stripe account and search Stripe docs from any agent

---
Source: https://chatgptplugins.directory/mcp/cloudflare-workers-bindings · Index: https://chatgptplugins.directory/llms.txt · Independent and community-run. Not affiliated with or endorsed by OpenAI. ChatGPT is a trademark of OpenAI.