cloudflare-workers-mcp: Instructions file for Claude Code

CLAUDE.md

cloudflare-workers-mcp CLAUDE.md is an instructions file for Claude Code from daniil-shumko/cloudflare-workers-mcp. It costs 1,303 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for a local MCP server that manages Cloudflare Workers. Cloudflare Workers are programs hosted on Cloudflare, and MCP lets Claude use the server's tools.

In plain words
What is it for?
Use it when installing dependencies, compiling the TypeScript code, running development mode, or modifying features for Cloudflare deployments, domains, versions, logs, or scheduled triggers.
Why use it?
It gives Claude the repository-specific commands, build steps, and API guidance needed to change this server safely. It also points to the project's implementation plan and development workflow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is daniil-shumko/cloudflare-workers-mcp's own configuration. It tells Claude Code how to work on cloudflare-workers-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cloudflare-workers-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to daniil-shumko/cloudflare-workers-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/daniil-shumko/cloudflare-workers-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/daniil-shumko/cloudflare-workers-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cloudflare-workers-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cloudflare-workers-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/daniil-shumko/cloudflare-workers-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,303 This file is loaded in full into every session.
When invoked 1,303 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01303 $0.01303
Opus 5 $0.00651 $0.00651
Sonnet 5 $0.00261 $0.00261
Haiku 4.5 $0.00130 $0.00130

Measured 10d ago against content hash 3e3b6ca77482, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cloudflare-workers-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is an MCP (Model Context Protocol) server for managing Cloudflare Workers: deploying static sites and Worker scripts, and managing versions, deployments, custom domains, and cron triggers. It connects via stdio transport for use with Claude Desktop and Claude Code.

Project status: feature-complete v1. All six milestones (M1–M6) are implemented — 22 tools covering static-site deploys (the headline feature), script lifecycle, versions/deployments/rollback, domains/subdomain/cron, and log queries. Read IMPLEMENTATION_PLAN.md before changing API-facing code — it carries verified API endpoint documentation (including the static-asset direct-upload protocol) and the design gotchas; all endpoint facts were re-verified against live Cloudflare docs on 2026-07-13.

This repo is the successor to cloudflare-pages-mcp (local: ~/workspace/personal/cloudflare-pages-mcp, now in maintenance mode). The architecture deliberately mirrors it — when in doubt about a pattern (summarizers, error suggestions, live-test guarding), the pages repo is the worked example with 21 tools.

Commands

# Install dependencies
npm install

# Build (compile TypeScript to dist/)
npm run build

# Development mode with watch
npm run dev

# Type checking only (no emit)
npm run typecheck

# Run the server
npm start

# Tests (Node's built-in test runner via tsx — no extra framework)
npm test               # unit + protocol smoke (safe, no creds, CI-ready)
npm run test:unit      # pure-logic units, fully mocked fetch
npm run test:protocol  # builds, then drives the real server over the MCP stdio wire
npm run test:live      # guarded live e2e: deploys/serves/deletes a throwaway cf-mcp-test-* site
npm run typecheck:test # type-check the test files too (tsconfig.test.json)

See test/README.md for the test layering.

Read the full file on GitHub · 127 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 127 lines · 1,303 tokens per session scan A 3e3b6ca77482

Subscribe to this mod's changes

cloudflare-workers-mcp CLAUDE.md is an instructions file published in the GitHub repository daniil-shumko/cloudflare-workers-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,303 tokens to every session, about $0.0065 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.