okaneland-mcp
Provides current, human-verified pricing for 100+ AI tools and calculates AI product margins (MRR after costs). Fetches live price index and runs locally.
README
@okaneland/mcp
A small Model Context Protocol server that gives AI agents two things from Okane Land:
| Tool | What it does |
|---|---|
get_ai_tool_prices |
Current, human-verified pricing for 100+ AI tools solo builders use, with what's free, what a real month costs, the gotcha, and the last-verified date. Fetched live from the maintained price index. |
calculate_ai_margin |
Turns an AI product's MRR into what you actually keep after the token bill, card fees, failed payments, refunds, and tax, plus the break-even price and usage cap. |
It runs on the user's machine over stdio, so there is nothing to host. get_ai_tool_prices fetches the public /api/v1/prices.json at call time, so the data is always as fresh as the site's monthly re-verification.
Install
Add it to your MCP client's config (Claude Desktop, Cursor, Windsurf, and others use the same shape):
{
"mcpServers": {
"okaneland": {
"command": "npx",
"args": ["-y", "@okaneland/mcp"]
}
}
}
Restart the client. The two tools appear in any agent you run there.
Example
You: I want a $20/mo AI writing tool on Claude Sonnet. What do similar tools charge, and would $20 keep money at 500 users?
The agent calls get_ai_tool_prices and calculate_ai_margin, then answers from real data: comparable tools charge more, and at 500 users on a Sonnet-class blend you keep about $3,260/mo (33%), staying profitable down to a $12.25 price or up to 3.3M tokens per user.
Tool reference
get_ai_tool_prices
Inputs (all optional): category, query, id, limit. Returns the matching tool rows plus the index's updated date, method, and source page.
calculate_ai_margin
Inputs: pricePerMonth, payingCustomers, blendedTokenPricePerM, tokensPerUserM, and optional monthlyChurnPct (6.1), intlCardPct (40), vatPct (0), failedPaymentsPct (9), refundsPct (3). Returns gross, tokenBill, cardFees, failedPayments, refunds, tax, keep, keepPct, perCustomerKeep, customersReplacedMonthly, breakEvenPrice, breakEvenTokensPerUserM, and tokenCostExceedsPrice.
Privacy
The server fetches only the public price index over HTTPS and sends nothing about you. The margin calculation runs entirely locally.
Develop
npm install
npm run build # tsc -> dist/
npm test # unit tests pin the margin math to the web calculator
npm run smoke # spins up the server, runs the MCP handshake, calls both tools
The margin math in src/margin.ts is a port of Okane Land's margin calculator; src/margin.test.ts pins its known-good outputs so the two cannot silently drift.
Disclaimer
Numbers are directional, not financial advice.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.