Building a Remote MCP Server on Cloudflare (Without Auth)

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

RightBlogger MCP gives any AI agent direct access to SEO keyword research, Google Search Console performance, and your WordPress/Ghost/Webflow CMS — research keywords, read posts, and pull GSC data straight from Claude, Cursor, or any MCP client.

EU legal research for AI agents: semantic + full-text search over ~48,000 EUR-Lex acts including consolidated versions, daily drift monitoring, answers with verifiable CELEX citations. German, English, French. Remote MCP server at https://conformi.eu/api/mcp — free tier, no key required for article and timeline tools.

AI image generation using various models

Analyze your workout history, manage routines, track progress, and help you plan future training using your real fitness data from Hevy

Your AI agent just got a marketing team. SendPulse MCP Server provides full access to the SendPulse marketing platform — email campaigns, CRM, chatbots, SMTP, and online courses. 134 methods across 5 modules.

Check your portfolio, cash transactions, movements, payed fees, growth history and more

Engagement marketplace on Base, native to the Bankr ecosystem: AI agents and communities fund quests (follows, reposts, replies, quotes, original posts); verified-X humans complete them and are paid per approved action from a non-custodial x402 escrow — in USDC, BNKR, or any Bankr-launched token.

Your AI can ship landing pages now. Convika is a landing page ops platform built for MCP clients. Connect from Claude, Claude Code, Codex, or any MCP-compatible AI client and manage the full landing page lifecycle in natural language: - Create a LP and preview it before going live - Publish to a global edge network (pages stay up independently of the dashboard) - Collect leads with forms and export submissions - Read basic analytics: traffic, sources, devices, conversions, and goals - Connect custom domains - Iterate safely with version history and one-step rollback Quick start: 1. Sign up free at https://app.convika.com/signup 2. Claude Desktop: Settings → Connectors → Add custom connector → https://mcp.convika.com Claude Code: claude mcp add --transport http convika https://mcp.convika.com 3. Ask your AI: "Create a landing page for my product and show me the preview." Auth: OAuth 2.1 — sign in with your Convika account when the client prompts you.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。 如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

test

Swipe-to-review GitHub PRs with AI context. Paste a repo URL, get open PRs as a card stack with risk scores, AI summaries, similar past changes, and contributor history. Works as a Claude MCP plugin — review PRs directly from Claude Desktop or Cursor without a browser. 12 tools including risk scoring, semantic similarity search, caller lookup, and test coverage detection.

Remote govcon intelligence MCP for US federal + SLED contracting: semantic opportunity search, USASpending awards, recompete pipeline, congressional policy intel, GAO protests, capture/teaming, and 32 read-only tools. Streamable HTTP at https://mcp.primerfp.com/mcp.

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

solnk is a social media management platform that lets you schedule and publish content to nine networks — Instagram, TikTok, YouTube, X, LinkedIn, Pinterest, Facebook, Threads, and Bluesky — from one place. Its MCP server lets AI agents draft and publish social posts through a single interface, with a draft-first safety model so nothing goes live without review. Includes a content calendar, team approval workflow, and analytics. Start free at solnk.com.

Generates high-quality unit tests for Python code with a coverage before/after report on every run. Derives concrete edge cases (None inputs, numeric boundaries, empty collections, exception paths) and returns ready-to-run pytest files with external I/O automatically mocked. Free tier: 100 executions. Pro: $19/month.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Scan and fix a domain's email deliverability (SPF, DKIM, DMARC, MTA-STS, TLS-RPT, BIMI, DNS blocklists) — and remediate the DNS at the registrar.

LLMtoMD turns your docs into clean, AI-ready Markdown and serves them to Cursor, Claude Code, and any MCP client so your coding agent retrieves your spec instead of forgetting it.

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

LinkedIn for AI agents. Agents register structured profiles, list projects, evaluate fit via FitReports, and propose connections — all through a hosted MCP server. 27 tools, zero install. Handlers (humans) approve connections. Built on Cloudflare Workers + KV.

MCP Advisor & Installation - Use the right MCP server for your needs

Describe a real-world problem in plain language and Matchbox finds products built to solve it - with reasoning, honest caveats, what each product won't cover, and a frank 'no strong match' when nothing fits. The catalog (~12,000 products) focuses on early-stage and lesser-known products that search engines and LLM training data usually miss. Never sponsored; payment never affects ranking. Tools: find_products_for_problem, search_catalog, get_product. No auth required.

EchoRelay is a multi-tenant HTTP relay: callers hit your versioned API lines, EchoRelay authenticates, rate-limits, and bills the request, then fans it out to your target URLs with retries and a dead-letter queue. The MCP server is the management plane — your agent can set up and operate a project end to end: create lines and endpoints, dry-run endpoint configs, manage API keys and key policies, invite team members, check billing and credits, read request logs and metrics, and retry or discard DLQ entries. Every tool carries read-only/destructive annotations, so MCP hosts can auto-approve reads and confirm destructive actions. Authentication is a Bearer token created in the EchoRelay panel. Docs: https://docs.echorelay.dev — pricing: https://echorelay.dev/pricing

An MCP server that flattens Claude Code sessions — keeping every prompt and event verbatim while reclaiming context tokens, so you resume the exact same raw conversation at a lower token count instead of compacting it into a lossy summary. It moves bulky tool output (large file reads, command logs, base64 screenshots) into a sidecar file, leaving a tiny retrievable reference in its place. Crash-safe, idempotent, and fully reversible. Real example from the README: a 317,236-token session flattened to 182,287 tokens.

Healthy Food MCP is a public MCP server that gives AI agents structured access to healthy recipe content. It lets Claude, Cursor, Gemini, and other MCP-compatible clients browse recipes by calorie category, diet group, meal type, macros, and keywords. The server includes tools for listing recipe categories, exploring diet and meal groups, browsing available recipe files, fetching full structured recipes, and searching the recipe collection. It is designed as a practical example of how MCP can be used beyond developer tools — turning curated food knowledge into something AI agents can query, understand, and use in real conversations. Healthy Food MCP is powered by Vectoralix and includes connection metadata, plugin manifests, reusable skills, documentation, assets, and validation scripts for easier installation and testing.