PreReason
Financial market context for AI agents, with listed companies' results: www.prereason.com/agents.md
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"@prereason/mcp"
]
}
}
}Runnable packages
0.9.1stdioRemote endpoints
https://api.prereason.com/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (7)
🟢list_briefings(tier, search)
List 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.
Input Schema
{
"type": "object",
"properties": {
"tier": {
"type": "string",
"enum": [
"free",
"basic",
"pro"
],
"description": "Filter briefings by subscription tier (free, basic, or pro). Returns all tiers if omitted."
},
"search": {
"type": "string",
"maxLength": 200,
"description": "The question or its key words (for example \"is the yield curve inverted\" or \"Toyota earnings\"). Returns the matching briefings, best first, at most five, and any covered companies it names (at most five)."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_metrics(category, search)
List the individual metrics, among them the Fed balance sheet, M2 supply, Treasury yields, net liquidity, the dollar, cross-asset indices (SPY, QQQ, VXX, UUP) and Bitcoin price and hash rate. Use it to find a metric's name for get_metric; for a reasoned view across several series, use list_briefings. Filter by category or by a search word. No authentication required.
Input Schema
{
"type": "object",
"properties": {
"category": {
"type": "string",
"enum": [
"bitcoin",
"calculated",
"eth",
"macro"
],
"description": "Filter by metric category: bitcoin, calculated, eth, macro"
},
"search": {
"type": "string",
"maxLength": 100,
"description": "Search term to filter metrics by name or description"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_health(verbose)
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.
Input Schema
{
"type": "object",
"properties": {
"verbose": {
"type": "boolean",
"description": "Include detailed endpoint descriptions and data coverage info. Defaults to false."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_context(briefing, entity, block, history, format, ...)
Get a pre-reasoned market briefing with trends and confidence scores, plus regime classification and a rule based note on what moved with the price in the briefings that carry them, for the requested domain (macro, rates, bonds, FX, commodities, a listed company, cross-asset or Bitcoin; the same families as the server instructions). Output is written to be read directly by reasoning agents, not parsed for individual values. Find the briefing id with list_briefings first, which also gives each briefing's plan; for one data series rather than a briefing, use get_metric. Needs a PreReason account: a signed in connection or an API key.
Input Schema
{
"type": "object",
"properties": {
"briefing": {
"type": "string",
"enum": [
"btc.quick-check",
"btc.context",
"macro.snapshot",
"cross.correlations",
"btc.pulse",
"btc.grid-stress",
"btc.momentum",
"macro.liquidity",
"macro.auctions",
"macro.calendar",
"cross.ai-compute",
"macro.rates",
"btc.on-chain",
"cross.breadth",
"btc.miner-survival",
"btc.full",
"btc.factors",
"cross.regime",
"fx.liquidity",
"btc.energy",
"btc.treasury",
"btc.etf-flows",
"commodities.gold",
"commodities.silver",
"commodities.copper",
"commodities.wheat",
"commodities.energy-basket",
"commodities.oil-producers",
"commodities.gold-miners",
"commodities.grains-agribusiness",
"eth.context",
"bonds.context",
"bonds.full",
"equities.company"
],
"description": "Briefing ID to fetch"
},
"entity": {
"type": "string",
"pattern": "^(?:[A-Za-z0-9.-]{1,12}|[A-Za-z0-9]{18}[0-9]{2})$",
"description": "The company for a per company briefing: the ticker or CIK of a company filing with the US securities regulator (NVDA), a Japanese securities code (7203), a Korean stock code (005930), an Indian company's ISIN (INE018A01030), the LEI of a company filing in the UK or of a European company (2138002P5RNKC5W2JZ46) or a B3 ticker (PETR4), with briefing=equities.company"
},
"block": {
"type": "string",
"enum": [
"header",
"what_changed",
"situations",
"against_guidance",
"numbers",
"segments",
"valuation",
"capital_structure",
"quality",
"profitability",
"news"
],
"description": "One part of the company briefing, with entity (for example \"valuation\" or \"against_guidance\"); today only, except \"numbers\", which also takes date (its figures as known on that day). Leave out for the whole briefing. A part counts one call; the whole briefing counts one for each part it carries."
},
"history": {
"type": "boolean",
"description": "With block \"numbers\" alone: the numbers block with its core lines over the last eight quarters, or the half years a company files instead, and five fiscal years, as filed. One call; never part of the whole briefing."
},
"format": {
"type": "string",
"enum": [
"json",
"markdown"
],
"default": "markdown",
"description": "Response format: markdown (human-readable, default) or json (structured data)"
},
"date": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "A past date, YYYY-MM-DD: the briefing as of the end of that day (UTC; a company's numbers at the end of the day in its own market), for the periods released by then. Each figure says when it was public, or that it may be a later revision PreReason holds in its place. For a period's latest figures, including later corrections, leave date out. Tier-gated: Free=30d; Basic=3y, Bitcoin briefings from Jan 2025; Pro=all. A company briefing takes one only with block \"numbers\"."
}
},
"required": [
"briefing"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_metric(metric, format)
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.
Input Schema
{
"type": "object",
"properties": {
"metric": {
"type": "string",
"enum": [
"bitcoin-price",
"bitcoin-market-cap",
"bitcoin-volume-24h",
"bitcoin-change-24h",
"bitcoin-dominance",
"bitcoin-hash-rate",
"bitcoin-difficulty",
"bitcoin-tx-count",
"bitcoin-tx-volume",
"bitcoin-active-addresses",
"fed-balance",
"m2-supply",
"treasury-10y",
"rrp",
"eur-usd",
"cny-usd",
"krw-usd",
"inr-usd",
"gbp-usd",
"chf-usd",
"yield-curve",
"tga",
"treasury-3mo",
"treasury-2y",
"treasury-5y",
"treasury-30y",
"treasury-1mo",
"treasury-1-5mo",
"treasury-2mo",
"treasury-4mo",
"treasury-6mo",
"treasury-1y",
"treasury-3y",
"treasury-7y",
"treasury-20y",
"breakeven-5y",
"breakeven-10y",
"real-yield-20y",
"real-yield-30y",
"breakeven-20y",
"breakeven-30y",
"t5yifr",
"t10y3m-spread",
"auction-bid-to-cover-10y",
"auction-bid-to-cover-30y",
"indirect-bidder-pct",
"dealer-takedown-pct",
"next-treasury-auction-days",
"fed-funds-rate",
"ecb-deposit-rate",
"boj-policy-rate",
"fed-ecb-spread",
"fed-boj-spread",
"carry-trade-returns-proxy",
"carry-trade-velocity-1d",
"iwm-spy-credit-spread",
"spy-vxx-correlation-30d",
"regime-stability-flag",
"jpy-usd",
"oil-brent",
"oil-wti",
"real-rate-10y",
"gld-gdx-ratio",
"copper-gold-ratio",
"slv-sil-ratio",
"gdxj-gdx-ratio",
"gold-silver-ratio",
"brent-wti-spread",
"oil-wti-realized-vol-30d",
"etf-gld-1h-velocity",
"etf-cper-1h-velocity",
"etf-uup-velocity-1h",
"crude-oil-stocks",
"natgas-storage",
"oil-inventory-zscore",
"natgas-storage-zscore",
"ecb-boj-spread",
"etf-gld-volume",
"etf-uso-volume",
"etf-uup-volume",
"etf-gld-volume-zscore-30d",
"etf-uso-volume-zscore-30d",
"etf-uup-volume-zscore-30d",
"net-liquidity",
"hash-ribbon",
"etf-spy",
"etf-qqq",
"etf-iwm",
"etf-vxx",
"etf-uup",
"etf-gld",
"etf-gdx",
"etf-gdxj",
"etf-slv",
"etf-sil",
"etf-cper",
"etf-weat",
"etf-tlt",
"etf-ibit",
"usdt-market-cap",
"usdt-dominance",
"btc-price-200d-ma",
"btc-price-200d-distance",
"btc-etf-net-flow",
"btc-etf-cumulative-flow",
"btc-etf-aum",
"btc-etf-ibit-flow",
"btc-etf-fbtc-flow",
"btc-etf-gbtc-flow",
"btc-etf-other-flow",
"btc-etf-ibit-aum",
"btc-etf-fbtc-aum",
"btc-etf-bitb-aum",
"btc-etf-arkb-aum",
"btc-etf-btco-aum",
"btc-etf-ezbc-aum",
"btc-etf-brrr-aum",
"btc-etf-hodl-aum",
"btc-etf-btcw-aum",
"btc-etf-gbtc-aum",
"btc-etf-btc-aum",
"bitcoin-price-1h-change-pct",
"raw-hashprice-tick",
"on-chain-velocity-30d",
"bitcoin-volume-zscore-30d",
"btc-perp-oi-contracts",
"btc-perp-positioning-regime",
"btc-perp-funding-zscore-30d",
"btc-realized-vol-7d",
"btc-realized-vol-30d",
"btc-realized-vol-90d",
"cot-spx-noncomm-net",
"cot-spx-noncomm-net-percentile-26w",
"cot-spx-noncomm-net-percentile-52w",
"cot-spx-noncomm-net-percentile-156w",
"cot-gold-noncomm-net",
"cot-gold-noncomm-net-percentile-26w",
"cot-gold-noncomm-net-percentile-52w",
"cot-gold-noncomm-net-percentile-156w",
"cot-crude-noncomm-net",
"cot-crude-noncomm-net-percentile-26w",
"cot-crude-noncomm-net-percentile-52w",
"cot-crude-noncomm-net-percentile-156w",
"cot-jpy-noncomm-net",
"cot-jpy-noncomm-net-percentile-26w",
"cot-jpy-noncomm-net-percentile-52w",
"cot-jpy-noncomm-net-percentile-156w",
"cot-eur-noncomm-net",
"cot-eur-noncomm-net-percentile-26w",
"cot-eur-noncomm-net-percentile-52w",
"cot-eur-noncomm-net-percentile-156w",
"cot-treasury10y-noncomm-net",
"cot-treasury10y-noncomm-net-percentile-26w",
"cot-treasury10y-noncomm-net-percentile-52w",
"cot-treasury10y-noncomm-net-percentile-156w",
"cot-copper-noncomm-net",
"cot-copper-noncomm-net-percentile-26w",
"cot-copper-noncomm-net-percentile-52w",
"cot-copper-noncomm-net-percentile-156w",
"cot-silver-noncomm-net",
"cot-silver-noncomm-net-percentile-26w",
"cot-silver-noncomm-net-percentile-52w",
"cot-silver-noncomm-net-percentile-156w",
"cot-wheat-noncomm-net",
"cot-wheat-noncomm-net-percentile-26w",
"cot-wheat-noncomm-net-percentile-52w",
"cot-wheat-noncomm-net-percentile-156w",
"cot-btc-cme-dealer-net",
"cot-btc-cme-asset-manager-net",
"cot-btc-cme-leveraged-funds-net",
"cot-btc-cme-other-reportable-net",
"cot-btc-cme-nonreportable-net",
"cot-btc-cme-open-interest",
"cot-eth-cme-dealer-net",
"cot-eth-cme-asset-manager-net",
"cot-eth-cme-leveraged-funds-net",
"cot-eth-cme-other-reportable-net",
"cot-eth-cme-nonreportable-net",
"cot-eth-cme-open-interest",
"nyfed-sofr",
"nyfed-sofr-p1",
"nyfed-sofr-p25",
"nyfed-sofr-p75",
"nyfed-sofr-p99",
"nyfed-sofr-volume",
"nyfed-bgcr",
"nyfed-bgcr-p1",
"nyfed-bgcr-p25",
"nyfed-bgcr-p75",
"nyfed-bgcr-p99",
"nyfed-bgcr-volume",
"nyfed-tgcr",
"nyfed-tgcr-p1",
"nyfed-tgcr-p25",
"nyfed-tgcr-p75",
"nyfed-tgcr-p99",
"nyfed-tgcr-volume",
"nyfed-effr",
"nyfed-effr-p1",
"nyfed-effr-p25",
"nyfed-effr-p75",
"nyfed-effr-p99",
"nyfed-effr-volume",
"nyfed-obfr",
"nyfed-obfr-p1",
"nyfed-obfr-p25",
"nyfed-obfr-p75",
"nyfed-obfr-p99",
"nyfed-obfr-volume",
"tic-treasury-holdings-total",
"tic-treasury-holdings-foreign-official",
"tic-treasury-holdings-japan",
"tic-treasury-holdings-united-kingdom",
"tic-treasury-holdings-china",
"tic-treasury-holdings-belgium",
"tic-treasury-holdings-cayman-islands",
"tic-treasury-holdings-luxembourg",
"tic-treasury-holdings-canada",
"tic-treasury-holdings-ireland",
"tic-treasury-holdings-france",
"tic-treasury-holdings-taiwan",
"tic-net-foreign-purchases-long-term",
"tic-net-foreign-purchases-treasuries",
"tic-net-foreign-purchases-agency-bonds",
"tic-net-foreign-purchases-corporate-bonds",
"tic-net-foreign-purchases-equities",
"tic-net-foreign-official-purchases-treasuries",
"korea-exports-20d",
"korea-chip-exports-20d",
"auction-dealer-share-2y",
"auction-dealer-share-3y",
"auction-dealer-share-5y",
"auction-dealer-share-7y",
"auction-dealer-share-10y",
"auction-dealer-share-20y",
"auction-dealer-share-30y",
"eia930-demand-daily-us48",
"eia930-demand-daily-erco",
"eia930-demand-daily-pjm",
"eia930-peak-demand-us48",
"eia930-peak-demand-erco",
"eia930-peak-demand-pjm",
"nyfed-srf-daily",
"boc-policy-rate",
"rba-cash-rate",
"rbnz-cash-rate",
"snb-policy-rate",
"riksbank-policy-rate",
"norges-bank-policy-rate",
"pboc-loan-prime-rate",
"bok-base-rate",
"rbi-repo-rate",
"boe-bank-rate",
"us-core-cpi",
"u6-unemployment-rate",
"labor-force-participation-rate",
"average-hourly-earnings",
"wb-gold-usd-oz",
"wb-silver-usd-oz",
"wb-copper-usd-mt",
"wb-wheat-srw-usd-mt",
"bank-reserves",
"nyfed-soma-total",
"us-debt-total",
"ecb-balance",
"eu-cpi",
"nyfed-primary-dealer-treasury-net",
"nyfed-soma-treasuries",
"us-debt-public-held",
"eu-m3",
"germany-10y",
"france-10y",
"italy-10y",
"spain-10y",
"portugal-10y",
"greece-10y",
"belgium-10y",
"france-germany-10y-spread",
"italy-germany-10y-spread",
"spain-germany-10y-spread",
"portugal-germany-10y-spread",
"greece-germany-10y-spread",
"belgium-germany-10y-spread",
"japan-10y",
"japan-30y",
"japan-40y",
"etf-hyg",
"etf-lqd",
"ethereum-volume-24h",
"ethereum-volume-zscore-30d",
"eth-staking-apr",
"ethereum-price",
"eth-200d-distance",
"nonfarm-payrolls",
"unemployment-rate",
"us-cpi",
"initial-jobless-claims"
],
"description": "Metric name to fetch"
},
"format": {
"type": "string",
"enum": [
"json",
"markdown"
],
"default": "markdown",
"description": "Response format: markdown (default) or json"
}
},
"required": [
"metric"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_changes(cursor, types, companies, limit)
What changed since your last call: the change events PreReason records. A live briefing's state label changing, a tracked release becoming known, and, for the companies you name, figures stored for a newer period, an event driven situation turning on, and filed news. Each event says what changed, when it happened, when PreReason knew it and where to read it next (the briefing or metric to fetch with get_context or get_metric); it carries no value. For the filed and official records themselves, by date, use get_news. Pass the next_cursor of your previous call to read only what is new; without one, the last 24 hours. Needs a PreReason account with basic access or above: a signed in connection or an API key.
Input Schema
{
"type": "object",
"properties": {
"cursor": {
"type": "string",
"pattern": "^[0-9]{1,18}$",
"description": "The next_cursor of your previous call. Left out, the read starts from the last day of events."
},
"types": {
"type": "array",
"items": {
"type": "string",
"enum": [
"state.changed",
"release.published",
"company.figures_updated",
"company.situation_changed",
"company.news"
]
},
"description": "The event types to read. Every type when left out."
},
"companies": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 200,
"description": "Companies whose events to read: the ticker or CIK of a company filing with the US securities regulator (NVDA), a Japanese securities code (7203), a Korean stock code (005930), an Indian company's ISIN (INE018A01030), the LEI of a company filing in the UK or of a European company (2138002P5RNKC5W2JZ46) or a B3 ticker or a Brazilian company's CNPJ (PETR4). At most 200. A company's events reach only a call that names it."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Events one call returns, 1 to 100. Default 50."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_news(about, kind, since, until, as_of, ...)
Dated records of what companies filed and what federal agencies and the Federal Reserve published, newest first, each with its source, its date or time and a link. Name a company in `about` for its filings alone; `kind` narrows to filed or official records; `since` and `until`, or `as_of`, set the window. Every answer names the sources it read. It states records, not reasons. For what changed since your last call, use get_changes; this tool reads the records themselves, by date. Needs a PreReason account: a signed in connection or an API key.
Input Schema
{
"type": "object",
"properties": {
"about": {
"type": "string",
"minLength": 1,
"maxLength": 40,
"description": "One company, by ticker or ISIN. Left out, records of every company and agency read."
},
"kind": {
"type": "string",
"enum": [
"filed",
"official"
],
"description": "filed (company filings) or official (federal agency and Federal Reserve documents). Both when left out."
},
"since": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The first date of the window, YYYY-MM-DD. Seven days before until when left out."
},
"until": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "The last date of the window, YYYY-MM-DD. Today (UTC) when left out."
},
"as_of": {
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"description": "Only records dated on or before this date, YYYY-MM-DD; in place of until."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Records one call returns, 1 to 25. Default 10."
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence