Mcp Cloudflare
Helps with MCP tools, Cloudflare as part of orchestrating AI agents and multi-step workflows workflows.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add mcp-cloudflare npx -- -y @trustedskills/mcp-cloudflare
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"mcp-cloudflare": {
"command": "npx",
"args": [
"-y",
"@trustedskills/mcp-cloudflare"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill enables AI agents to interact with Cloudflare services using Model Context Protocol (MCP). It provides access to various Cloudflare resources including Workers, KV, R2, D1, Hyperdrive, Observability data, Builds, Audit logs, and the Container Sandbox. The skill facilitates troubleshooting and changes within multi-step workflows by persisting evidence and artifacts to disk, passing only file paths between agents.
When to use it
- Investigating Cloudflare service performance issues using observability data.
- Managing Workers Bindings (KV, R2, D1) in a controlled workflow.
- Automating build processes for Cloudflare Workers.
- Auditing changes made within your Cloudflare account.
- Creating or modifying Cloudflare resources as part of an automated process requiring confirmation and verification.
Key capabilities
- Access to Cloudflare services via MCP (Workers, KV, R2, D1, Hyperdrive, Observability, Builds, Audit, Container Sandbox).
- File-based pipeline for persisting evidence and artifacts between agents.
- Read-only access (Diagnose Tier) for querying observability data, build history, and audit logs.
- Write operations (Change Tier) for managing Workers Bindings, buckets, namespaces, requiring user confirmation.
- Browser rendering capabilities: fetching HTML content, converting to Markdown, and taking screenshots of web pages.
Example prompts
- "Show me the error rate for my worker 'my-worker' over the last hour."
- "List all KV namespaces in account 'my-account'."
- "Create a new R2 bucket named 'test-bucket' in account 'my-account'."
- “Take a screenshot of https://www.example.com”
Tips & gotchas
- The skill utilizes a specific directory structure for evidence and plan management:
runs/<workflow>/active/<run_id>/. - Write operations (Change Tier) require user confirmation before execution and post-execution verification.
- The "Super Admin" tier, granting access to the Container Sandbox, is restricted to isolated environments or test accounts due to its elevated privileges.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.