mcp-server

mcp-server is a cursor rule for Cursor from adshaa/salla-mcp-server. It costs 23 tokens per session (1,364 once invoked), scanned A, original, MIT.

Rules for creating a remote MCP server on Cloudflare. The described template includes user authentication and both free and paid tools, with payments handled through Stripe.

In plain words
What is it for?
Use it to build or extend a Cloudflare Worker MCP server with Google or GitHub sign-in, Stripe payments, webhooks, and free or paid tools.
Why use it?
It provides a starting structure for connecting an MCP server to Cloudflare services, login flows, stored authentication data, and paid access.

Cursor rule for Cursor

Install

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.

agentmods
npx agentmods add rules/adshaa/salla-mcp-server/mcp-server
Clone the repo
git clone --depth 1 https://github.com/adshaa/salla-mcp-server

Made for: Cursor.

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 mcp-server

README.md
[![agentmods](https://agentmods.dev/badge/rules/adshaa/salla-mcp-server/mcp-server.svg)](https://agentmods.dev/rules/adshaa/salla-mcp-server/mcp-server)
Your own site
<a href="https://agentmods.dev/rules/adshaa/salla-mcp-server/mcp-server"><img src="https://agentmods.dev/badge/rules/adshaa/salla-mcp-server/mcp-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,364 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00023 $0.01364
Opus 5 $0.00012 $0.00682
Sonnet 5 $0.00005 $0.00273
Haiku 4.5 $0.00002 $0.00136

Measured 4d ago against content hash 6a442d75b327, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/mcp-server.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Boilerplate Project Overview

This rule provides a guide to understanding the structure and core functionalities of the MCP Boilerplate project. It's designed to help you navigate and extend the boilerplate effectively.

Core Architecture

The project is a Cloudflare Worker that implements an MCP (Model Context Protocol) server with built-in support for user authentication and Stripe payments.

  • Main Entry Point: src/index.ts

    • Initializes the BoilerplateMCP agent, which extends PaidMcpAgent from @stripe/agent-toolkit/cloudflare.
    • Sets up routing using Hono, handling the homepage (@src/pages/index.html), payment success page (@src/pages/payment-success.html), and Stripe webhooks (@src/webhooks/stripe.ts).
    • Configures the OAuthProvider for handling authentication flows, defaulting to Google (@src/auth/google-handler.ts) but switchable to GitHub (@src/auth/github-handler.ts).
  • Configuration:

    • wrangler.jsonc: Defines Cloudflare Worker settings, including Durable Objects (BoilerplateMCP), KV namespaces (OAUTH_KV for storing OAuth related data), and compatibility flags.
    • package.json: Lists project dependencies like @modelcontextprotocol/sdk, @stripe/agent-toolkit/cloudflare, hono, zod, and OAuth providers. It also contains scripts for development (dev) and deployment (deploy).
    • .dev.vars (from @.dev.vars.example): Stores local development secrets and environment variables such as API keys for Google, GitHub, Stripe, and BASE_URL.

Tool Creation

MCP tools are defined in the src/tools/ directory. Each tool is typically in its own file and then exported via src/tools/index.ts to be registered in src/index.ts within the BoilerplateMCP.init() method.

  • Free Tools:
    • Defined using agent.server.tool().
    • Example: @src/tools/add.ts (simple addition) and @src/tools/calculate.ts (more complex calculations).
    • Input parameters are validated using zod.

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 23 tokens per session scan A 6a442d75b327

Subscribe to this mod's changes

mcp-server is a cursor rule published in the GitHub repository adshaa/salla-mcp-server (7 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 1,364 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 2026-08-31.