> ## Documentation Index > Fetch the complete documentation index at: https://docs.ctxprotocol.com/llms.txt > Use this file to discover all available pages before exploring further. # Introduction > A pay-per-response data marketplace that feeds grounded context to AI agents. Built on MCP, Context connects users, builders, and developers.
Context Protocol Hero Context Protocol Hero
Open Context Build with Node.js Build with Python *** **LLMs are smart, but they lack the live facts your question actually needs.** Context is a gateway to premium data feeds (the market intelligence normally locked behind steep monthly or annual subscriptions), unbundled into pay-per-response. Your agent buys exactly the facts a question needs at query time and drops them into its context window, so you get grounded, precise answers instead of confident guesses, without paying for a subscription you'd barely use. > **The insight you pay \$500/year for? Your agent could buy it for \$0.10/response.** ## Why use Context? * **Grounded Answers, Not Guesses:** Every response is assembled from live data the agent actually retrieved, or it tells you the marketplace can't answer, instead of inventing numbers. * **One Interface, Everything:** Stop integrating APIs one by one. Use a single SDK to access any tool in the marketplace. * **Zero-Ops:** We're the gateway to premium data tools that are usually locked behind steep monthly or annual subscriptions. We host the connections; you just send the JSON and get the result. * **Agentic Discovery:** Your Agent can search the marketplace at runtime to find tools it didn't know it needed. * **Simple Pricing:** Pay per response for curated intelligence, or pay per call for raw data. Your choice. *** ## The Ecosystem Context is not just a chatbot. It's an **economic engine for the AI era**. We connect three distinct groups in a decentralized marketplace for [Model Context Protocol (MCP)](https://modelcontextprotocol.io) tools. Build a standard MCP server, paste your endpoint URL, set a price, and get paid in USDC when agents use your tool. *** ## For Users: The Context Agent Ask anything and get a **grounded answer** built from live data: the agent buys the facts it needs on demand instead of guessing from stale training data. Real-time, read/write access to the world, one wallet, pay-per-response. Ask *"Find the best yield on Base"* and the Agent autonomously searches the marketplace, buys the necessary data tools, analyzes the returns, and presents the answer. Pay for everything (from gas data to premium stock analysis) using a single USDC balance. No subscriptions, just pay-per-response. Want proof? See [Grounded vs. Synthetic](/why-context/free-llm-comparison): the same hard market question sent to a top frontier model and to Context, where the free model invents the market regime and Context returns grounded numbers, a rendered chart, and a verifiable verdict. *** ## For Tool Builders: The "App Store" for MCP Monetize your data **without building a frontend**. Turn the insights people pay \$500/year for into \$0.10/response revenue you keep. | Benefit | Description | | ------------------------------- | ------------------------------------------------------------------------------------------------------------- | | **Build Once, Sell Everywhere** | Create a standard MCP Server | | **Zero UI Required** | You provide the API; our Agent provides the interface | | **Instant Revenue** | Set a price (e.g., \$0.01/response). Get paid in USDC on Base every time an Agent successfully uses your tool | *** ## For App Developers: The Universal Adapter Build your own agents using the Context Protocol as your **infrastructure layer**. Every API you integrate means reading docs, managing auth keys, handling rate limits, parsing a unique response schema, and maintaining it when they change. Multiply that by 5 data sources and you've lost a week before writing any business logic. Instead of integrating CoinGecko, Tavily, and Weather APIs separately, just install `@ctxprotocol/sdk` (TypeScript) or `ctxprotocol` (Python). One auth token, one interface, consistent typed schemas. Your agent can search the marketplace at runtime: `client.discovery.search("gas prices")`. It finds tools it didn't know existed and uses them without human intervention. Every tool exposes full Input/Output schemas. Your LLM can self-construct arguments and execute tools it has never seen before, with no hardcoded integrations. Give your agent a spending limit (`maxSpendUsd: "2.00"`) and let it explore. You control exactly how much it can spend per session. *** ## The npm/pip for AI Capabilities **"Context Protocol is npm/pip for AI capabilities."** Just as `npm install` or `pip install` gives you code other people wrote, Context gives your Agent **capabilities other people built**. ```typescript TypeScript theme={null} import { ContextClient } from "@ctxprotocol/sdk"; const client = new ContextClient({ apiKey: "sk_live_..." }); const answer = await client.query.run("What are the top whale movements on Base?"); console.log(answer.response); ``` ```python Python theme={null} import asyncio from ctxprotocol import ContextClient async def main(): async with ContextClient(api_key="sk_live_...") as client: answer = await client.query.run("What are the top whale movements on Base?") print(answer.response) asyncio.run(main()) ``` **Want more control?** The SDK also supports [Execute mode](/sdk/reference#tools-execute-mode) for per-call pricing with spending limits, which fits custom agent pipelines. See the [Agentic Pattern](/sdk/agentic-pattern) guide or the [SDK Reference](/sdk/reference). Start querying with Context Monetize your MCP server Integrate the SDK into your agents