StoQuant — Quantitative Stock Research
NPM · STOQUANT-MCP
StoQuant: 61 tools — Q-Score, ML, screeners, alt-data, portfolio, backtest, strategy.
Available components
Last scanned (4 hours ago)
Scores higher than 45% of npm servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 64 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 7692 tokens (~120/item across 64 items; 61 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management60
- Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage88
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 63% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 61 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 63 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 0
- Security disclosure: unverified → fail ▼ functional
- 1 Nov 26 +1
- Security disclosure: fail → unverified ▼ functional
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 −4
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/stoquant-mcp@0.6.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
stoquant_get_strategy_preset_candidates Get ranked candidates for a strategy preset ~86
Current ranked candidate tickers and target-weight basket for a themed preset (`social`, `insider`, `congress`, …). Returns `{preset, appliedOptions, candidates, basket}`. This is a signal read — it does NOT create or rebalance a paper portfolio.
| Name | Type | Req | Description |
|---|---|---|---|
| presetId | string | yes | Preset id from stoquant_list_strategy_presets |
No output schema declared.
No examples provided.
stoquant_get_top_conviction Get top-conviction picks ~81
StoQuant's current highest-conviction names: the stocks with the strongest Q-Scores backed by multiple corroborating signals. Use as the starting point for 'what does the platform like right now'. May be empty between scans (`{stocks:{}}`).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results (default 10, max 50) |
No output schema declared.
No examples provided.
stoquant_get_trending_social Get trending tickers (social) ~64
Most-mentioned tickers across social platforms in the last few hours, each with mentionCount, prevMentionCount, deltaPercent, velocityScore, bullishPct, and platforms. Use for market-wide 'what is retail talking about right now' discovery and early momentum.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
stoquant_get_unusual_options Get unusual options activity ~258
Options contracts trading far above their open interest, ranked by notional (volume x price x 100). Each row under `data.rows` has ticker, optType (call/put), strike, expiry, dte, volume, openInterest, volOi, newPosition (open interest was 0), notional, priceSource (mid/last), lastVsMid and ageHours. IMPORTANT: this is a delayed QUOTE snapshot, front-month expiry only — there is no trade tape, so no buyer/seller side and no sweep detection; `lastVsMid` is only where the last print sat between bid (0) and ask (1). Open interest is published next day, so volume/OI compares today against yesterday. Descriptive, not a buy or sell signal.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max rows, default 100, cap 500 |
| minNotional | number | – | Minimum dollars traded, e.g. 250000 |
| newPositionsOnly | boolean | – | Only contracts where open interest was 0 |
| ticker | string | – | Filter to one ticker; omit for the market-wide feed |
| type | string | – | Contract side (NOT the side of the trade) |
No output schema declared.
No examples provided.
stoquant_list_backtest_templates List backtest strategy templates ~83
The pre-built strategy templates you can backtest (`id`, name, parameters). Known ids include `momentum`, `growth_chaser`, `value`, `insider_follower`, `gem_composite`, and `research_*` variants. Call this before stoquant_run_backtest so you pass a real strategyId. Power-tier. Read-only.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
stoquant_list_prebuilt_screens List prebuilt screens ~169
List the curated prebuilt screens with their id, name, and description. Available screens: 'undervalued-gems' (low P/E, P/B value plays), 'momentum-leaders' (strong price momentum), 'oversold-bounce' (RSI reversal setup), 'ml-outperform' (ML-predicted S&P 500 outperformance), 'hidden-gems' (small-cap value with confirmation signals), 'growth-explosion' (high-growth micro/mid-caps before discovery), 'pre-explosion' (multibagger pattern: revenue acceleration + insider + fundamentals). Call this first, then run one with stoquant_run_prebuilt_screen — it is faster and better-tuned than hand-built filters.
| Name | Type | Req | Description |
|---|---|---|---|
| universe | string | – | – |
No output schema declared.
No examples provided.
stoquant_list_strategy_presets List themed strategy presets ~58
Themed strategy presets (social / insider / congress, etc.) with customization knobs. Read-only signal catalog — does not create a portfolio. Use stoquant_get_strategy_preset_candidates to see the current ranked basket for one preset.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
stoquant_optimize_portfolio Optimize portfolio weights (Black-Litterman) ~174
Compute target weights via Black-Litterman (HRP blend fallback). Returns an `optimization` object with weights — it does NOT place orders, rebalance, or move cash. If `predictions` is omitted the server fills views from ML forecasts (up to 20 tickers). Pro/Power tier. Use the weights as a recommendation; call stoquant_get_accuracy_summary first and do not size into buys while excessSpreadPp is negative and dataSufficient is true.
| Name | Type | Req | Description |
|---|---|---|---|
| initialCapital | number | – | Starting capital in USD (informational) |
| method | string | – | Optimizer method (only black-litterman is supported) |
| predictions | object | – | Optional views keyed by ticker. Omit to auto-fetch ML predictions. |
| tickers | array | yes | Universe to allocate across |
No output schema declared.
No examples provided.
stoquant_run_backtest Run a historical backtest ~189
Run a historical backtest for a strategy template over [startDate, endDate]. Returns the full run (metrics at 0% slippage plus bias disclosure: Deflated Sharpe, iteration count). This is a simulation — it does NOT place live or paper orders. It does persist a run record you can reload with stoquant_get_backtest. Power-tier; computationally expensive (this call can take tens of seconds). Prefer universe=sp500. Dates are YYYY-MM-DD.
| Name | Type | Req | Description |
|---|---|---|---|
| endDate | string | yes | YYYY-MM-DD inclusive end |
| initialCapital | number | – | Starting capital USD (default 100000) |
| startDate | string | yes | YYYY-MM-DD inclusive start |
| strategyId | string | yes | Template id from stoquant_list_backtest_templates, e.g. momentum, value, gem_composite |
| universe | string | – | Default sp500 |
No output schema declared.
No examples provided.
stoquant_run_prebuilt_screen Run a prebuilt screen ~131
Run one curated screen by its id (from stoquant_list_prebuilt_screens) and get the ranked matching stocks. Prefer this over stoquant_run_screener for common intents (value, momentum, oversold, ML picks, hidden gems, growth) — the filters are pre-tuned. universe defaults to sp500; use 'full' for the broadest set. Result count is fixed by the screen definition.
| Name | Type | Req | Description |
|---|---|---|---|
| screenId | string | yes | Screen id, e.g. 'undervalued-gems' or 'momentum-leaders' |
| universe | string | – | – |
No output schema declared.
No examples provided.
stoquant_run_screener Run a custom screen ~406
Run a custom stock screen. Read-only — nothing is mutated. All filters are AND-combined; returns an ARRAY of matching stocks (ticker, name, price, plus the requested metrics and overlays like valueScore/qScore/mlProbability). Valid filter fields (camelCase, case-sensitive): trailingPE, forwardPE, priceToBook, marketCap, epsTrailingTwelveMonths, dividendYield, bookValue, regularMarketPrice, fiftyDayAverage, twoHundredDayAverage, fiftyDayAverageChangePercent, twoHundredDayAverageChangePercent, regularMarketChangePercent, fiftyTwoWeekHighChangePercent, regularMarketVolume, averageDailyVolume3Month, sector, industry, rsi14, twentyDayAverageChangePercent, oneHundredFiftyDayAverageChangePercent, shortPercentOfFloat, grossMargins, operatingMargins, profitMargins, returnOnEquity, returnOnAssets, debtToEquity, revenueGrowth, earningsGrowth, pegRatio, currentRatio, numberOfAnalystOpinions. Additional sort-only fields: valueScore, qScore, marginOfSafety, mlProbability. Margins/growth are decimals (0.25 = 25%); marketCap is raw USD (250M = 250000000). An unknown field is rejected with a suggestion (it would otherwise silently return zero matches). For per-field units and typical ranges, read the stoquant://screener-fields resource. Tip: a full-universe scan can be slow and time out — prefer universe='sp500' and a handful of filters, or use stoquant_run_prebuilt_screen.
| Name | Type | Req | Description |
|---|---|---|---|
| filters | array | yes | Filter conditions, all must match (AND) |
| limit | integer | – | Max results (default 50, max 100) |
| sortDirection | string | – | – |
| sortField | string | – | Field to sort by (any valid field, or valueScore/qScore/marginOfSafety) |
| universe | string | – | – |
No output schema declared.
No examples provided.
How do I install the StoQuant — Quantitative Stock Research MCP server?
StoQuant — Quantitative Stock Research runs locally as an npm package, launched with npx -y stoquant-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · stoquant-mcp
claude mcp add ohadf2015-stoquant-mcp -- npx -y stoquant-mcp
What is the StoQuant — Quantitative Stock Research MCP server?
StoQuant — Quantitative Stock Research is an MCP server listed in the public MCP registry as io.github.ohadf2015/stoquant-mcp. StoQuant: 61 tools, Q-Score, ML, screeners, alt-data, portfolio, backtest, strategy. This page covers its npm package (stoquant-mcp).
Is the StoQuant — Quantitative Stock Research MCP server safe to use?
StoQuant — Quantitative Stock Research scores 73 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the StoQuant — Quantitative Stock Research MCP server expose?
StoQuant — Quantitative Stock Research exposes 61 tools: stoquant_get_quote, stoquant_get_quotes_batch, stoquant_get_extended_quote, stoquant_get_sparklines, stoquant_get_benchmarks, and 56 more. Their descriptions and schemas cost roughly 6,880 tokens of context every time the server is loaded.
Is the StoQuant — Quantitative Stock Research MCP server still maintained?
StoQuant — Quantitative Stock Research is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the StoQuant — Quantitative Stock Research MCP server under?
StoQuant — Quantitative Stock Research declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.