Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add secondsky/claude-skills --skill cloudflare-mcp-servergit clone --depth 1 https://github.com/secondsky/claude-skillsWrote 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.
[](https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-mcp-server)<a href="https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-mcp-server"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-mcp-server.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00488 |
| Opus 5 | $0.00013 | $0.00244 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
cloudflare-mcp-server 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 4d 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.
What it actually says
Cloudflare MCP Server
Last Updated: 2025-11-21
Quick Start
import { McpServer } from '@modelcontextprotocol/sdk';
const server = new McpServer({
name: 'my-server',
version: '1.0.0'
});
server.tool('getTodo', async ({ id }) => ({
id,
title: 'Task',
completed: false
}));
export default server;
Core Concepts
- Tools: Functions AI can call
- Resources: Data AI can access
- Prompts: Reusable templates
- Transports: SSE, HTTP, WebSocket
Example Tool
server.tool('searchDocs', {
description: 'Search documentation',
parameters: {
type: 'object',
properties: {
query: { type: 'string' }
}
},
handler: async ({ query }) => {
return { results: [...] };
}
});
Resources
Core Documentation
references/quick-start-guide.md(704 lines) - Official Cloudflare templates, complete step-by-step workflow, 5-minute setupreferences/core-concepts.md(66 lines) - MCP fundamentals: tools, resources, prompts, transportsreferences/worker-basics.md(326 lines) - Worker & Durable Objects basics, transport selection, HTTP fundamentalsreferences/stateful-servers.md(246 lines) - Durable Objects integration, WebSocket hibernation, cost optimization, common patternsreferences/production-deployment.md(814 lines) - Deployment & testing, configuration reference, authentication patterns, 22 known errors with solutions
Templates
templates/basic-mcp.ts- Minimal MCP servertemplates/tools-example.ts- Tool definitionstemplates/durable-object-mcp.ts- Stateful MCP with DOtemplates/websocket-mcp.ts- WebSocket transport
Official Docs: https://modelcontextprotocol.io | Cloudflare: https://developers.cloudflare.com/workers/runtime-apis/durable-objects/
What ships with it
26 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/authentication.md 9.1 KB
- references/common-issues.md 6.8 KB
- references/core-concepts.md 1.6 KB
- references/debugging-guide.md 13 KB
- references/error-catalog.md 268 B
- references/http-transport-fundamentals.md 10 KB
- references/oauth-providers.md 4.6 KB
- references/official-examples.md 4.2 KB
- references/production-deployment.md 18 KB
- references/quick-start-guide.md 17 KB
- references/stateful-servers.md 5.0 KB
- references/transport-comparison.md 9.4 KB
- references/transport.md 2.6 KB
- references/worker-basics.md 7.0 KB
- templates/basic-mcp-server.ts 6.4 KB runs code
- templates/basic-mcp.ts 257 B runs code
- templates/claude_desktop_config.json 751 B
- templates/mcp-bearer-auth.ts 16 KB runs code
- templates/mcp-http-fundamentals.ts 8.4 KB runs code
- templates/mcp-oauth-proxy.ts 9.1 KB runs code
- templates/mcp-stateful-do.ts 8.2 KB runs code
- templates/mcp-with-d1.ts 19 KB runs code
- templates/mcp-with-workers-ai.ts 11 KB runs code
- templates/package.json 555 B
- templates/wrangler-basic.jsonc 903 B
- templates/wrangler-oauth.jsonc 2.1 KB
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.
- 4d ago First seen · 70 lines · 26 tokens per session scan A 2a1c59bb9f5c
cloudflare-mcp-server is a skill published in the GitHub repository secondsky/claude-skills (215 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 488 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
remember
Record why something is the way it is — a decision and its reasoning, a lesson that cost time, or a standing constraint. Use when the reasoning behind a choice would be expensive to reconstruct later.
bootstrap
Set up chamnan in this repository for the first time — build the architecture index, measure how well the code describes itself, fill in missing file comments, and record a baseline. Run once per repo.
milestone
Record a change that reshaped the repository — what moved, why it was worth doing, and which areas it touched. Use after a migration, a rewrite, or a decision that changed how part of the system works.
resume
Write down where this stretch of work stopped, so the next session continues instead of restarting. Use at the end of a working session, or when handing the repository to someone else.
capture
Write down a procedure worth keeping — a multi-step process, a trap that cost real time, or something that has now come up three times. Use it the moment you finish such a task, while the details are still exact.
promote
Turn a scratch script into a permanent tool this repo keeps. Use when a check, report, or analysis has proved worth running more than once.