PreReason

Created By

PreReason4 days ago

Pre-reasoned Bitcoin and macro market context that AI agents can actually use. 17 briefings covering BTC price, hash rate, difficulty, mining production costs, treasury holdings (30 public companies), Fed balance sheet, M2 supply, Treasury yields, and cross-asset correlations. Returns markdown by default because numbers are AI's weakest input and language is its strongest skill. Each briefing includes trend direction, confidence scores, percentile rankings, regime classification, and causal narratives. JSON also available. Free tier, API key or x402 USDC micropayments.

# bitcoin

# macro

Overview Content Tools Comments

Overview

What PreReason Does

Every financial API gives you numbers. Your agent then has to figure out what those numbers mean, how they relate to each other, whether they're high or low historically, and what direction they're moving. That interpretation step is where agents fail.

PreReason does the interpretation before your agent ever sees the data. One API call returns a complete market briefing with trend direction, confidence score, percentile ranking against the last 90 days, regime classification (risk-on, risk-off, transition), and a causal narrative connecting the signals.

Markdown by default. Not because JSON doesn't work, but because language is what LLMs are built to process. Raw numbers force your agent into its weakest mode. Structured language keeps it in its strongest.

17 Briefings, 3 Tiers

Free (6): btc.quick-check, btc.context, btc.pulse, btc.grid-stress, macro.snapshot, cross.correlations

Basic (5): btc.momentum, btc.on-chain, btc.miner-survival, macro.liquidity, cross.breadth

Pro (6): btc.full, btc.factors, btc.energy, btc.treasury, cross.regime, fx.liquidity

30 Metrics

Bitcoin: price, market cap, hash rate, difficulty, active addresses, transaction volume

Macro: Fed balance sheet, M2 supply, Treasury 10Y yield, reverse repo, net liquidity, yield curve

Cross-asset: SPY, QQQ, VXX, UUP (as BTC correlation signals, not standalone coverage)

Mining: production cost models with fleet-weighted ASIC efficiency across 17 hardware eras

Treasury: 30 public company BTC holdings from SEC filings and CoinGecko

How to Connect

MCP (recommended for AI agents): Use npx with @prereason/mcp and set PREREASON_API_KEY in your env config.

REST API: curl -H "Authorization: Bearer YOUR_API_KEY" https://api.prereason.com/api/btc

x402 (keyless, pay per call): Send USDC on Base with your request. 0.01 USDC for free-tier briefings, 0.02 USDC basic, 0.03 USDC pro.

Server Config

{
  "mcpServers": {
    "prereason": {
      "command": "npx",
      "args": [
        "-y",
        "@prereason/mcp"
      ],
      "env": {
        "PREREASON_API_KEY": "your-api-key"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

ChatWiseThe second fastest AI chatbot™

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.

Tavily Mcp

RedisA Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

DeepChatYour AI Partner on Desktop

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

CursorThe AI Code Editor

Baidu Map百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

Zhipu Web SearchZhipu 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.