PreReason MCP Server
@PreReason
基本信息
关于 PreReason MCP Server
MCP server for PreReason, the Context API for financial agents. 17 pre-reasoned market briefings with trend signals, regime classification, confidence scores, and cross-asset correlations.
PreReason MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"prereason": {
"command": "npx",
"args": [
"-y",
"@prereason/mcp"
],
"env": {
"PREREASON_API_KEY": "your-api-key"
}
}
}
}PreReason MCP Server 工具
8List the pre-reasoned market briefings, each with its tier requirement, and the company briefing (equities.company), one listed company per call. Covers macro, rates, bonds, FX, commodities, listed companies, cross-asset and Bitcoin. Call it first to find the briefing id for a question, then read that briefing with get_context. Pass search with the question's words to get only the briefings that match, best first; when it names a company, the answer also lists the matching covered companies, each with the entity to pass to get_context. For one data series rather than a briefing, use list_metrics. Every covered company, by market, is listed at GET https://api.prereason.com/api/companies, with no key needed. No authentication required.
List the individual metrics, among them the Fed balance sheet, M2 supply, Treasury yields, net liquidity, the dollar, cross-asset indices (SPY, QQQ, VXX, UUP) and Bitcoin price and hash rate. Use it to find a metric's name for get_metric; for a reasoned view across several series, use list_briefings. Filter by category or by a search word. No authentication required.
Check API health status, version, and available endpoints. Use it to confirm the server answers or to read its version; it carries no market data, so use list_briefings or list_metrics to find data. No authentication required.
Get a pre-reasoned market briefing with trends and confidence scores, plus regime classification and a rule based note on what moved with the price in the briefings that carry them, for the requested domain (macro, rates, bonds, FX, commodities, a listed company, cross-asset or Bitcoin; the same families as the server instructions). Output is written to be read directly by reasoning agents, not parsed for individual values. Find the briefing id with list_briefings first, which also gives each briefing's plan; for one data series rather than a briefing, use get_metric. Needs a PreReason account: a signed in connection or an API key.
Get a single metric with pre-reasoned signal interpretation, trend analysis (7d/30d/90d), confidence score with factor breakdown, momentum, and percentile ranking. Name the metric; list_metrics lists them and searches them by word. Needs a PreReason account: a signed in connection or an API key. Returns analyzed context (signal, trend direction, momentum, percentile among every stored daily close), not raw values. The signal is bullish, bearish or neutral on crypto series, and above-trend, below-trend or at-trend on every other metric, where the value sits against its trend, so a high yield reads above-trend. Use it to read where a metric stands against its trend and its own history, not just its number; for a reasoned view across several series, use get_context with a briefing. Every plan reads each metric's latest reading. Pro and above read every metric in full; on other plans, a metric outside the plan returns its latest reading only.
What changed since your last call: the change events PreReason records. A live briefing's state label changing, a tracked release becoming known, and, for the companies you name, figures stored for a newer period, an event driven situation turning on, and filed news. Each event says what changed, when it happened, when PreReason knew it and where to read it next (the briefing or metric to fetch with get_context or get_metric); it carries no value. For the filed and official records themselves, by date, use get_news. Pass the next_cursor of your previous call to read only what is new; without one, the last 24 hours. Needs a PreReason account with basic access or above: a signed in connection or an API key.
Dated records of what companies filed and what federal agencies and the Federal Reserve published, newest first, each with its source, its date or time and a link. Name a company in `about` for its filings alone; `kind` narrows to filed or official records; `since` and `until`, or `as_of`, set the window. Every answer names the sources it read. It states records, not reasons. For what changed since your last call, use get_changes; this tool reads the records themselves, by date. Needs a PreReason account: a signed in connection or an API key.
Connect this assistant to the user's PreReason account. Call it when the user asks to connect, link, sign in to or log in to PreReason, or when a PreReason tool answers AUTH_REQUIRED. Until the account is connected it returns one link for the user to open: they sign in, or create a free account, and click Approve. No key is ever shown; it arrives in this connection by itself. Call it again after they approve: it says whether the account is connected, and on which plan.
概览
PreReason gives an AI agent financial market context it can reason with.
It is a financial data MCP server and REST API: ask what a listed company reported, where Treasury yields stand or what the Federal Reserve decided, and one call returns a briefing reasoned in advance, with the figures, their dates and sources, a one line reading, trend direction over several windows, confidence scores, percentile ranks and correlations, and in the deeper briefings a regime label and a plain language narrative.
Briefings span asset classes and regions, among them the economy and the economic calendar, interest rates and Treasury yields, bonds, currencies, commodities and energy, listed companies across markets read from their own reports and filings, and Bitcoin.
The set grows as markets and asset classes are added; list_briefings and list_metrics always return the current one.
Each briefing carries the figures behind its readings, every figure is dated, and every briefing names its sources.
It is served over MCP (a remote server and an npm bridge) and over REST, as Markdown or JSON.
An AI agent starts at https://www.prereason.com/agents.md, which says how to connect, which briefings it can read and how to answer from them.
数据与分析 分类下的更多 MCP 服务器
OrbitWan.io
Wanchain explorer data and analytics: addresses, transactions, tokens, validators, cross chain transfers, plus OrbitPay prepaid premium data (x402).
Subtext
Subtext by FullstorySession replay, built for agents. Subtext is agentic session review: it captures production sessions of your app and connects them to your coding agent — Claude Code, Cursor, Codex, Devin, your own harness — so it can
App Store Tracker
Top In ItiOS App Store data for AI agents: chart rankings, app details, reviews, keywords, ads and revenue estimates for any app in any country.
Octolens
OctolensGive your AI agents every brand mention across the internet — 15+ platforms, AI-filtered, one structured feed.
Lawstronaut Legal Research
Lawstronaut-FZCOConnect your AI to millions of laws and court cases! Lawstronaut is the infrastructure layer that connects AI agents and software to millions of legal documents across 150+ jurisdictions, structured legal data, continuou
评论