prereason
Registry code: 84502213b1a645c1
PreReason returns financial market briefings with the interpretation already done: trends and confidence scores, and in the deeper briefings regime classification, for macro, rates, bonds, FX, commodities, listed companies and Bitcoin. Use it when a question depends on current market or macro context, such as what Treasury yields, the Fed balance sheet, M2, Treasury auctions or oil and gas inventories are doing, what a listed company reported, or where Bitcoin stands and how it moves with stocks, volatility and the dollar. Call list_briefings first to see what is available, then get_context…
- endpoint
- https://api.prereason.com/api/mcp
- door code
- b9a09f4d6ee739b3
- protocol
- https://modelcontextprotocol.io/specification/2025-11-25/basic/transports#streamable-http ·1.0
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 10 · newcomer
- Is prereason live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
- Is prereason free to use?
- Partly — some of its tools are open, others need a key or payment.
- What tools does prereason have?
- 10 tools: Macro Economic Indicators, Corporate Bitcoin Treasury Holdings, Rates and Bonds, Listed Company Briefings, Backtest Evidence, Cross-Asset Correlation Analysis, Bitcoin Market Intelligence, Mining Economics and Energy Analysis, ….
- Is prereason safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.4%· all time 99.2%
last good check
of 10 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- live → degraded· endpoint unreachable (timeout after 20000ms); card still served
- degraded → live
- used for
- get pre-reasoned market briefing
- get macro metric with trend signal
- see market changes since last call
- takes → gives
- text → data, text
Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. The address stands behind 40 doors on this origin, so the chain figures are the operator's. How it is counted.
through this hub
successful
what callers paid
distinct
last 2026-11-04
concentrated
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
macro-indicators unknown never probed
Fed balance sheet, M2 supply, Treasury 10Y yield, reverse repo, net liquidity, and yield curve with trend analysis and regime context.
treasury-intelligence unknown never probed
Corporate Bitcoin treasury holdings. From the companies' own filings and CoinGecko. Miner vs corporate split, accumulation trends, institutional adoption.
rates-bonds unknown never probed
Treasury yields across the curve, real yields and breakevens, the latest FOMC statement, Treasury auctions and who holds US Treasuries, each figure dated and its source named.
company-briefings unknown never probed
One listed company per call (USA, Japan, Korea, India, UK, France, Austria, Belgium, Denmark, Finland, Iceland, Italy, Lithuania, Netherlands, Slovenia, Slovakia, Sweden, Norway, Spain, Malta, Luxembourg, Greece, Hungary, Croatia, Portugal, Poland, Romania, Estonia, Latvia, Brazil and Hong Kong), each figure dated and its source named, read from the company's own filings.
backtest-evidence unknown never probed
7 simulated Bitcoin backtests over one window, measuring whether PreReason briefings change AI agents' decisions, with methods and results at https://www.prereason.com/evidence
cross-asset-correlations unknown never probed
BTC correlation matrix against SPY, QQQ, VXX, UUP. Market breadth and regime detection across asset classes.
btc-market-intelligence unknown never probed
Regime classification, confidence scores, trend analysis, momentum, percentile rankings, and a rule based note on what moved with the BTC price. Covers price, hash rate, difficulty, mining production costs, and treasury holdings.
mining-economics unknown never probed
Bitcoin production cost model, hashprice, hash ribbon, energy pressure from natural gas. Miner stress scoring, survival index, and profitability measures for mining sector analysis.
momentum-technical unknown never probed
90-day momentum with percentile rankings, the 200-day moving average, RSI-style trend strength and Bollinger bands, for research agents.
fx-commodities unknown never probed
The dollar and FX liquidity, US crude and gas inventories, gold, silver, copper and wheat, with trend direction and percentile ranks.
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id84502213b1a645c1.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/84502213b1a645c1/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/84502213b1a645c1?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.