HPSILab Quant Finance
Server Details
Stock & options risk analytics for AI agents: pre-trade risk scan, IV, gamma walls, Monte Carlo.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- haiyunsky/hpsilab-quant-finance-mcp
- GitHub Stars
- 1
- Server Listing
- HPSILab - Quant Finance MCP Server for Stock Analysis and Options Analytics
- ChatGPT
- –
- Claude
- HPSILab Quant Research
TDQS
Scored across 10 tools
The atomic analytics (get_ai_prediction, get_iv_radar, get_option_pressure, get_monte_carlo, get_equity_curve, get_pretrade_risk_scan) each target a clearly separate analysis. The main soft spot is the aggregation trio: analyze_stock, generate_stock_images, and generate_stock_research_report all bundle the same underlying data and are only separated by output format (JSON vs PNG URLs vs markdown) and pricing tier, which descriptions clarify but do not fully eliminate as a choice.
All names are snake_case with a leading verb (get_, generate_, analyze_, register_), forming a predictable verb_noun pattern throughout. The only wrinkle is inconsistency in the verb choice for similar operations and mismatched argument naming across the set (ticker in the get_* tools vs symbol in analyze_stock, generate_stock_images, generate_stock_research_report, get_pretrade_risk_scan).
Ten tools is comfortably within a well-scoped range for a quant analytics server, and each atomic analysis tool earns its place. The count is slightly inflated by three overlapping aggregation/reporting tools that largely re-compose the same underlying sources.
The surface covers the expected quant workflow: per-signal analytics, aggregation, chart images, a full research report, risk scanning, and account registration. The notable gap is watchlist management — get_equity_curve is defined around 'your watchlist', yet no tool lists or edits watchlist symbols, so the aggregate tool is not fully self-contained.
Publisher details
- Operator
- HPSILab · Publisher source
- Operator website
- https://hpsilab.com · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- Unknown
- Privacy policy
- Not provided
- Trust center
- Unknown
- Restrictions
- A free HPSILab account is required. MCP connections use OAuth 2.1 with PKCE and Dynamic Client Registration. An API key is issued automatically after authorization. Usage is metered against the account's Credits balance. HPSILab is for quantitative research and informational use only and does not provide investment advice. · Publisher source
Available Tools
10 toolsanalyze_stockStock AnalysisARead-onlyIdempotentInspect
Aggregate all quant tools into one JSON stock analysis.
The tool reuses the existing MCP tools as its data sources, then derives a
direction signal, direction score, bullish factors, bearish factors and
plain-English summary. `tool_responses` carries each source's full text
(AI prediction, IV radar, option pressure, equity curve, Monte Carlo with
its distribution), including their data dates; `confidence_score_meaning`
explains the 0-100 score. If one underlying tool is gated, unavailable or
raises an error, the remaining tools still contribute to the final result
(status "partial"); if every underlying tool fails, the whole call fails
(status "error", isError=True) instead of a misleadingly "successful"
empty analysis.
Args:
symbol: Stock symbol, e.g. "NVDA".
refresh: Request fresh IV Radar data instead of using the backend's
fresh IV cache. Defaults to False.
lang: Language for `summary`, `bullish_factors` and `bearish_factors`
- "en" (default), "zh" or "ja"; regional forms like "zh-CN" are
accepted. Everything else in the response, `signal` included, is
language-independent, so an existing caller that omits this gets
byte-identical output to before.
Inputs: symbol (required), lang, refresh. Returns: object
generate_stock_imagesStock Chart GeneratorAInspect
Generate stock-report PNG images and return their URLs, with the charts attached as PNG image content so the assistant can see them.
The JSON (symbol, status, images with url/status, disclaimer) is the same
with or without attachments; the image blocks are added after it.
Args:
symbol: Stock symbol, e.g. "RXRX".
force: Regenerate images instead of using cached PNGs. Defaults to True
so manually requested images reflect the latest available data.
types: Optional subset of chart types. Allowed values are
"ai_prediction", "iv_radar", "option_pressure", "monte_carlo",
and "equity_curves". Omit to generate every chart type.
attach_images: Attach each available chart as an image. Defaults to
True; False returns the JSON with URLs only.
Inputs: symbol (required), force, types, attach_images.
generate_stock_research_reportStock Research ReportAInspect
Full markdown research report with its most relevant stock-report charts attached as images. Pro tool ($0.35/call via x402 for anonymous callers; free within plan limits for signed-in accounts, subject to a monthly report quota).
Runs analyze_stock and stock-report image generation concurrently, then
renders a presentation-ready markdown report (direction, direction score, bullish /
bearish factors, source-tool status). The one or two most relevant charts are
attached as PNG image content; the markdown is returned for display and the
same data, with chart URLs, is mirrored in structured JSON.
Signed-in hpsilab users call this within their plan's free rate limits.
Anonymous / tokenless agents pay per call via x402 (USDC on Base) when
payments are enabled — send the x402 payment in the request _meta.
Args:
symbol: Stock symbol, e.g. "RXRX".
refresh: Bypass the backend's fresh IV cache for the IV-driven modules.
Defaults to False.
force_images: Force a fresh image render instead of reusing the backend's
image cache. Defaults to False.
Inputs: symbol (required), refresh, force_images.
get_ai_predictionAI PredictionARead-onlyIdempotentInspect
AI next-day prediction: probability the stock closes UP, a paper-trading buy/watch/sell lean (research only, not a trade instruction), and how strongly the models agree (consensus).
basis="live" (default) uses the latest available market data: while the
market is open that is today's still-trading bar, labelled intraday with
its computation time. basis="close" uses only the latest completed
session's close. Returns the model input date and close (and which of the
two it is), the model name, the blended UP probability and each of the two
models' (Random Forest, Logistic Regression) probabilities, whether they
agree, suggested stop-loss / take-profit, and the news sentiment with its
source (or a note that no headline was dated that day).
Available to every authenticated plan (Free / Pro / Enterprise); subject
to the caller's plan requests/day and requests/minute limits.
Args:
ticker: Stock symbol, e.g. "TSLA".
basis: "live" (default) or "close".
Inputs: ticker (required), basis.
get_equity_curveStrategy BacktestARead-onlyIdempotentInspect
Backtest performance of the quant strategy across your watchlist: Sharpe ratio, max drawdown, win rate and total return per symbol.
Available to every authenticated plan (Free / Pro / Enterprise); subject
to the caller's plan requests/day and requests/minute limits.
Args:
ticker: Optional symbol to show just one row, e.g. "SPY". Leave blank for all.
Inputs: ticker.
get_iv_radarImplied Volatility RadarARead-onlyIdempotentInspect
Implied-volatility (IV) structure for a stock: how expensive options are, whether volatility is being squeezed, and whether traders are paying up for upside (calls) or downside (puts). Available to all signed-in users.
Returns spot price, the expiry used, the option quote time (latest trade
in the chain, UTC) and fetch time, ATM and 30-day IV, IV rank/percentile
with their basis, the 25-delta risk reversal in vol points, a squeeze
score and the volatility regime.
Args:
ticker: Stock symbol, e.g. "NVDA".
refresh: Bypass the backend's fresh IV cache and request the latest
option-chain pull. Defaults to False.
Inputs: ticker (required), refresh.
get_monte_carloMonte Carlo SimulationARead-onlyIdempotentInspect
Monte Carlo price simulation for the next ~10 trading days: thousands of random price paths estimate a likely price range and the odds of finishing higher.
Returns the price-history date and starting close, mean and median
projected close, the 90% range, daily volatility, support/resistance and
the chance of finishing above resistance. It also returns the simulated
distribution of day-10 closes: percentiles (p5-p95), a 40-bin histogram
(price range and path count per bin) and a Gaussian KDE curve on the same
count scale - enough to chart the distribution as a histogram with the 90%
range, mean and resistance marked. The simulation is seeded from the price
history, so repeated calls on the same data return the same numbers.
Args:
ticker: Stock symbol, e.g. "AAPL".
Inputs: ticker (required).
get_option_pressureOptions Pressure MapARead-onlyIdempotentInspect
Option-chain pressure map for the nearest weekly/monthly expiry — Max Pain, dealer Gamma Wall, likely weekly high, and an extreme squeeze target.
Returns spot, the expiry and days to it, the option quote time (latest
trade in the chain, UTC), max pain, gamma/call/put walls, likely weekly
high, squeeze target, likely expiry close range, ATM IV and the weekly
expected move. Its expiry can differ from get_iv_radar's.
Args:
ticker: Stock symbol, e.g. "SPY".
Inputs: ticker (required).
get_pretrade_risk_scanPre-Trade Risk ScanAInspect
Full pre-trade risk scan JSON for a stock. Pro tool ($0.15/call via x402 for anonymous callers; Credits for signed-in accounts).
`riskDeltas` compares the SPY benchmark (`beforeValue`) with this stock on
its own (`afterValue`). Neither side is a portfolio, so it is not a
before/after of the caller's holdings; `exposure` and `correlation` are
the parts that use the holdings (see `methodology.riskDeltas`).
Signed-in hpsilab users (including Free, on its trial Credits) spend
Credits from their balance at this tool's catalog price — each tool is
priced differently; see GET /api/credits/catalog.
Anonymous / tokenless agents pay per call via x402 (USDC on Base) when
payments are enabled — send the x402 payment in the request _meta.
Args:
symbol: Stock symbol, e.g. "NVDA".
Inputs: symbol (required). Returns: object
register_accountRegister a Free AccountAInspect
Register a free hpsilab account for yourself, with no human involvement, and receive an API key immediately.
Call this when the user has no API key yet and asks to sign up from here,
or when a refusal's `next_actions` names register_account and the user
agrees. This is the only tool that works without an API key. You do not
need a password, a wallet, or a web browser. The account is bound to you
server-side, so calls you make after this are metered as your account even
though you cannot change your own Authorization header.
The account is created unverified, with only a capped evaluation
allowance and no trial Credits, until the email address is confirmed;
confirming it grants the one-time 100-Credit Registered Trial (14 days).
Ask the human you are working with to click the link in the email that
will arrive. Calling again from the same caller returns the same account
with a fresh key; an address that belongs to another account is refused.
A valid user email address is required. Do not call this tool with an
empty or fabricated email address. If the user's email is unavailable,
ask the user to provide it before calling register_account.
Args:
email: The real user email address that will receive verification.
Inputs: email (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Options analytics for AI assistants: chains, IV rank, VRP, Greeks, GEX, expected moves, screeners.
Trading journal, options risk checks, position sizing and Monte Carlo analytics for AI assistants.
Options flow, volatility, dealer positioning (GEX) and dark pool data for AI trading agents.
Options analytics: 17 pricing models, 17 Greeks, GEX, IV, 23 screeners, unusual, dark pool, max pain
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceConnects AI assistants to live options market data with 70+ tools for exposure analytics, volatility, strategy signals, and historical backtesting.1MIT
- AlicenseNot gradedqualityCmaintenanceProvides risk guardrails for AI trading agents by analyzing portfolio risk, checking trades against policies, and generating risk policies.60 PyPI3MIT
- AlicenseAqualityBmaintenancePoint-in-time market data for AI agents: stocks, ETFs and crypto as named bands plus raw values.105MIT
- AlicenseNot gradedqualityDmaintenanceThe verifiable risk engine for autonomous agents: deterministic, self-verifying financial calculations that an agent can delegate and prove. It covers liquidation and funding, position sizing and risk of ruin, options Greeks and margin, LP divergence, treasury concentration and depeg, execution quality checks, plus intelligence on options, DeFi, prediction markets, and transaction safety analysis.11 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.