MCP server that gives coding agents typed 0xArchive market data tools across Hyperliquid (perps, HIP-3, HIP-4, spot) and Lighter.xyz
Free
Tools
universe_summary
Orient the agent: total events, tickers, date range, top event types, top detectors, price coverage, SPY benchmark status. Call this FIRST when starting research. Returns counts that let the agent reason about sample sizes before drilling in.
ArgumentsA call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
—
p95 latency
—
call success
—
uptime 90d
0
calls last 7d
What it does
Quant-research MCP — tradeable signals from public-company website stack changes. 7 tools.
Quickstart
# 1 — install (mcprush login holds a key from your dashboard)
npx mcprush@latest add boolsai-signals-mcp
# 2 — ask your agent something
> Quant-research MCP — tradeable signals from public-company website stack changes. 7 tools.
Boolsai Signals is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
SIAll 1 server
signals.boolsai.ai1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add --transport http boolsai-signals-mcp https://signals.boolsai.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
What you approve
12 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Orient the agent: total events, tickers, date range, top event types, top detectors, price coverage, SPY benchmark status. Call this FIRST when starting research. Returns counts that let the agent reason about sample sizes before drilling in.
Takes no parameters.
Example callreturns →
Automated pattern discovery — scans event_type × detector × diff_field × severity combinations and returns those with the strongest forward-return characteristics (α vs SPY, % positive, n). Use this when you don't have a specific hypothesis yet. Returns sorted by α at +7D descending. Filter by min_n to set a sample-size floor.
Takes no parameters.
Example callreturns →
Compute α stats for an arbitrary filter expression. Use this to test a specific hypothesis (e.g. 'tier_count_changed on enterprise-SaaS tickers' or 'severity 5 events that happened on Mondays'). Returns n, mean/median raw and α returns at +1/+3/+7d, % positive, and the worst-loss trade.
Takes no parameters.
Example callreturns →
Live signal feed: events fired in the last N days (default 7). Returns each event with the predicted α range based on its event type's historical performance. Use this to surface 'what should I be looking at right now?'
Takes no parameters.
Example callreturns →
Deep dive on a single event: full diff (added/removed values), surrounding price action (-3D to +14D), predicted vs actual α, links to wayback comparison. Use this to investigate a specific event flagged by find_signals or recent_events.
Takes no parameters.
Example callreturns →
Scan a URL as it appeared on a historical date via the Wayback Machine. Uses intel.boolsai.ai against the wayback-wrapped URL. Returns the same JSON shape as Boolsai Scan but for a historical snapshot. Use when investigating WHEN a vendor was added/removed.
Takes no parameters.
Example callreturns →
All events fired on a single ticker, plus price action timeline. Use this to investigate one company's pattern (e.g. 'show me everything we caught on NFLX').
Takes no parameters.
Example callreturns →
Run an SPY-benchmarked backtest on the WAYBACK historical event dataset (2+ years, 13K events) instead of the recent live event dataset (2 months, 1.7K events). Much bigger samples for statistical confidence. Group by change_type / key_path / domain.
Takes no parameters.
Example callreturns →
Week-by-week wayback diff timeline for one domain. Returns every detected stack change (additions / removals) with week date. Use this to see when a vendor was added/removed historically, e.g. 'when did adobe.com add Segment?'
Takes no parameters.
Example callreturns →
ONE-SHOT cross-signal sweep. Computes α-vs-SPY stats simultaneously across event_type, detector, diff_field, severity, AND co_occurrence dimensions — returns the full landscape in a single response. Use this FIRST when you want to see where signal lives without having to call find_signals N times. Stateless, pure D1, no rate-limit risk, ~1s response. Cached per arg set for sub-100ms repeated queri
Takes no parameters.
Example callreturns →
Compare two signal patterns side-by-side. e.g. 'how does PRICING_TIERS_ADDED compare to VENDORS_DETECTED_CHANGED on the live dataset?' Returns α, %pos, sample size, worst/best trades for each, plus delta. Pure D1, fast.
Takes no parameters.
Example callreturns →
Bulk-farm a domain's historical wayback snapshots into our index. Use this when you need backtest history on a domain we haven't already farmed (i.e. wayback_backtest / domain_timeline return no data for it). Hits CDX → samples weekly → parallel-scans up to 50 snapshots via intel.boolsai.ai → inserts into wayback_intel_profiles. After farming completes you can call wayback_backtest or domain_timel
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Boolsai Signals costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
—Grade not published
No rule-by-rule report on file for this release
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is a hosted endpoint: the publisher runs it and we connect to it. The scanner reads packages and source, and neither exists to read here, so there is no grade — not a withheld one, an unmeasured one. What can be checked instead is on Installation: what it asks to reach and what it writes.
Release history
Pinned to 1.0.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
1.0.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Boolsai Signals in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.