Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Quant Swarm is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
1
downloads a day
local
or remote
36
downloads in 30d
What it does
Risk-first pre-trade checks, PIT data, leakage audits, and a Shadow Tournament vs a live champion.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user quant-swarm-mcp '--' uvx --from quant-swarm swarm-data-mcp
# 2 — ask your agent for something these tools do
# features.build, market.pulse, market.sentiment and 23 more
Quant Swarm costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user quant-swarm-mcp '--' uvx --from quant-swarm swarm-data-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://swarm-mcp-503318750546.europe-west1.run.app/mcp/data: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http quant-swarm-mcp https://swarm-mcp-503318750546.europe-west1.run.app/mcp/dataFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take SWARM_MCP_ACCESS_TOKEN (Optional access token from https://1.21initiative.com/mcp/ (free plan issued instantly). Without one, tools still list; calls return an access-required envelope) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
26 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.
Exact FEATURE_ORDER feature vector for symbol at session as_of, with provenance per field.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Ticker symbol, e.g. AAPL. |
| as_of | string | yes | Point-in-time session date (YYYY-MM-DD); every feature is a causal recomputation at this date, never a later revision. |
Derived-only technical snapshot: trend, volatility, oscillator, volume, and regime signals.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | no | Optional list of tickers to analyze via the shared cache/relay (default: none — supply symbols or your own bars). |
| bars | array | no | Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}] for symbols the shared cache does not carry. |
Derived-only sentiment/news snapshot for one symbol: headline count, earnings flag, and day-change bucket. Never returns raw quote values or headline text — quantized signals only. Not investment advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Ticker symbol, e.g. TSLA. |
Area-specific weather research for each symbol's operating footprint.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | yes | Tickers whose operating-area climate to research (registry-covered weather-exposed underlyings, or any ticker you supply areas for). |
| areas | array | no | Optional caller-supplied operating areas for underlyings outside the shipped registry: [{symbol, name?, lat, lon, weight?}]. Weather is fetched ONLY for these made/sold geographies — never the listing |
Is this alternative-data signal real for these tickers - or noise?
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | yes | Underlying tickers to query (max 10). Results are per underlying. |
| as_of | string | no | Point-in-time cutoff (YYYY-MM-DD, default today): release points after this date are ignored. |
| horizons | array | no | Subset of the run's horizons, e.g. ['1d','1w','1m','6m'] (default: all). |
| only_significant | boolean | no | Only return families with at least one SIGNIFICANT horizon (counts still cover everything). |
| max_families | integer | no | Max families returned per underlying, most significant first (1-100). |
Backfill history for a universe (default: the swarm's 13-symbol universe).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| universe | array | no | Optional list of tickers to backfill (default: the swarm's 13-symbol universe). |
| years | number | no | Years of daily history to backfill (max limited by the plan's backfill window). |
Cache inventory: rows per symbol, session bounds, depth in weeks, API-call accounting.
No parameter schema on file.
Toggle cache-only mode: no network access; reads served from cache, fetches refused.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | yes | True = cache-only mode (no network; reads from cache, fetches refused). |
Free tool — causal regime label per symbol (high_vol / drawdown / chop / melt_up / gap_heavy), derived from point-in-time bars with no lookahead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | no | Optional list of tickers to label via the shared cache/relay. |
| bars | array | no | Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}] for symbols the shared cache does not carry. |
Derived-only microstructure snapshot: order-flow imbalance, VPIN toxicity bucket, and effective half-spread — percentile-ranked within the series.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | no | Ticker to analyze (served from the shared cache/relay); omit when passing your own bars. |
| bars | array | no | Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}]. |
Derived-only volume forecast expressed as a ratio to the trailing 20-session average, with a 10th-90th percentile interval. Never returns raw share counts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Ticker to forecast (served from the shared cache/relay). |
| horizon_bars | integer | no | Number of sessions ahead to forecast (1-10). |
Ranked, derived-only screen over the symbol list — cross-sectional percentile ranks, never raw prices or volumes. Pro tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | no | List of tickers to screen (via the shared cache/relay); omit when passing your own bars. |
| bars | array | no | Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}]. |
| criteria | string | no | Screen criterion: breakout | momentum | volume | anomaly. |
Cross-sectional percentile rank of one derived metric across the symbol list — no raw metric values returned. Pro tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbols | array | no | List of tickers to rank (via the shared cache/relay); omit when passing your own bars. |
| bars | array | no | Optional caller-supplied OHLCV rows [{symbol, ts, open, high, low, close, volume}]. |
| metric | string | no | Metric to rank by: momentum_20d | volume_ratio_20d | atr_pct | rsi_14. |
Validate a proposed order against the house floors (max position 25%, gross cap 60%).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order | object | yes | Proposed order: {symbol, notional, side: buy|sell}. |
| equity | number | yes | Account equity (base currency) used for the exposure floors. |
| current_positions | object | no | Optional {symbol: notional} map of current positions. |
| floor_overrides | object | no | Optional per-fund overrides {max_position_pct, max_gross_exposure_pct}; the response always reports the deviation from the house floors. |
Audit a feature manifest for lookahead leakage and provenance violations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| manifest | array | yes | Feature manifest: [{name, source, value_ts, as_of}] to audit. |
| tape_started | string | no | Optional tape start date (YYYY-MM-DD); features predating it are flagged. |
| selected_symbols | array | no | Optional challenger-selected symbols for the coverage check. |
| snapshot_universe | array | no | Optional archived snapshot universe to measure coverage against. |
Convert a claimed gross edge into net-of-cost reality under the pessimistic fill model.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gross_edge_bps | number | yes | Claimed gross edge in basis points before costs. |
| spread_bps | number | yes | Average bid-ask spread in bps. |
| slippage_bps | number | yes | Expected slippage in bps. |
| adverse_selection_bps | number | yes | Adverse-selection drag in bps. |
Validate a genome against the bounded schema and return its canonical genome_hash.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| genome | object | yes | Genome object (bounded schema, versioned). |
Step-by-step mirror of the live C# risk engine sizing: ATR sizing, position-notional cap, overnight-gap halving, weekend gross headroom. Reports the house floors and any deviation when per-fund overrides are supplied.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| equity | number | yes | Account equity (base currency). |
| atr_14 | number | yes | 14-bar average true range of the instrument. |
| close | number | yes | Current close/reference price. |
| weekend_approaching | boolean | no | True when the position would be held into the weekend (gross headroom applies). |
| gross_exposure | number | no | Current portfolio gross exposure in currency. |
| overnight_gap | number | no | Expected overnight gap (price units); gaps above 1.2x ATR halve size. |
| floor_overrides | object | no | Optional per-fund overrides; deviation from house floors is reported. |
Request a promotion verdict. Always INDETERMINATE_LOCAL: the selection machinery is server-side. Names the exact missing statistical inputs and emits an audit_request plus a cloud_job spec for the hosted tournament.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| challenger_genome | object | yes | The challenger genome under evaluation. |
| champion_genome | object | no | Optional current champion genome; mutation tiers vs it are reported. |
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public; its licence metadata reads NOASSERTION rather than naming a licence
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Quant Swarm or to call it, 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: —
ATrust score 100 / 100
Release 0.5.0 · scanned 15 Oct 2026
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.
Threat score100
Client score100
Findings2 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest22f799e05c3137ec196a78d7d02c9841a1122466c0fa526ccb020824ff606fb3
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (26 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| features.build | no tags | |
| market.pulse | no tags | |
| market.sentiment | no tags | |
| market.climate | no tags | |
| pit.analysis | no tags | |
| cache.warm | no tags | |
| cache.stats | no tags | |
| cache.offline | no tags | |
| market.regime | no tags | |
| market.microstructure | no tags | |
| volume.forecast | no tags | |
| market.screen | no tags | |
| market.rank | no tags | |
| gym.label_regimes | no tags | |
| gym.probe_fragility | no tags | |
| gym.paired_preview | no tags | |
| gym.estimate_cloud_run | no tags | |
| tournament.submit | no tags | |
| tournament.verdict | no tags | |
| tournament.leaderboard | no tags | |
| warden.validate_order | no tags | |
| warden.audit_features | no tags | |
| warden.cost_check | no tags | |
| warden.validate_genome | no tags | |
| warden.explain_sizing | no tags | |
| warden.promotion_verdict | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest22f799e05c3137ec
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.5.0. Pin a release below and the command asks for exactly that one.
0.5.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Quant Swarm can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.