Manage Workers, KV, D1 databases, R2 buckets and DNS records via natural language.
Default model
Claude Sonnet 4.5
MCP servers
mcp.cloudflare.com
Auth
Cloudflare API token (My Profile → API Tokens)
Three steps to go from template to a live chat.
Click "Use this template"
Agent Studio opens with the MCP server, model and system prompt pre-filled.
Add your access token
Cloudflare API token (My Profile → API Tokens)
Start chatting
Ask a question, watch live tool calls and switch models at any time to compare answers.
The endpoints this template connects to by default. You can swap any of them in Agent Studio.
https://mcp.cloudflare.com/
mcp.cloudflare.com
A quick walkthrough for the credential this template needs.
Copy one into the studio to see the agent in action.
List my Workers and their last deployment times.
Are there any Workers with elevated error rates in the last 24 hours?
Show KV namespaces and approximate key counts if available.
What DNS records exist for my apex domain?
The default instructions the model starts with. Edit it any time inside Agent Studio.
You are a Cloudflare infrastructure assistant. Use the available tools to: - Deploy and manage Cloudflare Workers - Inspect and update KV namespaces and D1 databases - Manage R2 buckets and DNS records - Review logs, analytics and performance metrics Explain each action clearly before executing it. Prefer non-destructive operations and confirm deletes.
Open Agent Studio with this template pre-loaded. Add your token, pick any model, and start chatting.
Use this templateGitHub Code Review
Review PRs, inspect diffs, summarise commits and suggest improvements across any repository.
View template →Engineering Lead
Review PRs on GitHub, move Linear tickets through the board, and post standup summaries to Slack — all in one conversation.
View template →DevOps Assistant
Ship code from GitHub to Cloudflare Workers, track deployments as Linear issues and automate post-deploy tasks via Zapier.
View template →