omniparser-autogui-mcp

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

AgentLine is the telephony layer for AI agents. It gives your agent a real phone number making outbound calls, receiving inbound calls, and handling SMS all through a single API. No telecom infrastructure, no WebSocket wrangling, no separate STT/TTS providers to configure.

Web3 founder diligence: contract audit, jurisdiction matching, fund discovery, portfolio comparison, scoring. Free, open source.

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.

Find leads, enrich your contacts, and verify emails just by describing what you need. Versium REACH builds and sizes B2B and B2C audiences and fills in the contact and company data you're missing, all in plain language with no manual exports or API code. US data only. Estimates are free; building a list draws on your Versium account credits and always confirms with you first. Requires an active Versium REACH subscription with API access.

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

LiveAuth MCP Server gives AI agents cryptographic proof-of-work + Lightning Network authentication. Agents solve a PoW challenge, get a signed JWT, and use it to call paid MCP tools. Each tool call is metered in sats and recorded as a signed revenue event with a verifiable receipt. Built on L402 (the Lightning-Native HTTP 402 protocol from Lightning Labs). Compatible with x402 (Cloudflare/Coinbase). Non-custodial — no KYC, no account, no email. Pay per call in sats over Lightning. Install: `npx -y @liveauth-labs/mcp-server` Docs: https://docs.liveauth.app/mcp-liveauth-gate Source: https://github.com/dulzuradev/liveauth-mcp

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.

Trust ratings for AI agents and websites. Look up an agent's reputation, scan a site's AI-trust-readiness, and verify signed scorecards in-band — reads are zero-auth. From Mnemom, the trust layer for the agent internet.

An MCP (Model Context Protocol) server that generates advanced mock 2D PNG assets for games prototypes — directly from any MCP-compatible AI client such as Claude Desktop. This MCP is engine-agnostic and works with any game engine that supports PNG import: Godot Unity Unreal Engine GameMaker Construct RPG Maker And many more... Create placeholder sprites, UI elements, health bars, spritesheets, and more with full support for gradients, patterns, transparency, text rotation, and auto-scaling — all without opening an image editor. Each generated PNG embeds rich JSON metadata (dimensions, color, shape, description) directly in its EXIF data, so AI models without vision can still understand what an asset contains.

Bulk domain checking for AI chats: availability, aftermarket prices, archive.org history, social handle links, and buy links. Your AI brainstorms names; check_domains reports what's real for up to 50 names across 6 TLDs per call. Free to start — 20 credits. Setup: https://namebrewery.com/mcp

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

Calculate Human Design bodygraph charts from birth data, save people, compare charts, and analyse group dynamics — in any MCP client. Hosted remote server (Streamable HTTP, OAuth 2.0) by gethumandesign.com; free account to connect. Listed in the official MCP registry as com.gethumandesign.www/mcp.

Browser automation and web scraping

Hosted MCP server for source-provenanced US federal healthcare provider data — NPPES, CMS PECOS, Care Compare, OIG LEIE, Open Payments. Every field returns with its exact federal source, snapshot date, and SHA-256 attestation. Public data only; no PHI. Install: npx -y @fonteum/mcp

Remote MCP server exposing 8.7M+ registered charities across 60+ countries, sourced from official government registries (IRS, Charity Commission, ACNC, DSD, RNA, and 60+ more). Read-only, no key required to start.

MCP server for Wundervault zero-knowledge secret management. Exposes vault secrets to AI agents via the Model Context Protocol — secrets are decrypted server-side and never returned to the agent in plaintext.

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.

Retrieving and analyzing issues from Sentry.io

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 server that provides a tool for sending transactional emails via Mailtrap

Create a remote sandbox that can execute code/run commands/upload and download files. 创建远程沙盒，可以执行代码/运行命令/上传下载文件

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

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.

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

Save developer tools once — repos, CLIs, API docs — then let Claude, Cursor, and any MCP client search and recommend from your own curated catalog instead of generic model knowledge. Remote MCP over Streamable HTTP (OAuth 2.0 + DCR).

A Serper MCP Server

Create and manage short links - shorten URLs, list / inspect links, track credits. No subscriptions.

ERABI is the open, cryptographically auditable intent exchange for AI agents: register an identity in one command, discover providers ranked by reputation (never by payment), fire intents, and build verifiable reputation and earnings from dual-signed outcomes on a public hash-chained ledger. Zero-config — `npx -y erabi-mcp` joins the live public network with no accounts, no API keys. Six tools: register, discover, intent, report_outcome, my_reputation, my_earnings. Live explorer: https://erabi-explorer.vercel.app