Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ScalpStream Data

OCI · GHCR.IO/DV1-321/SCALPSTREAM-MCP

Pay-per-call air quality, US product recalls, border waits and cheapest fuel for AI agents via x402.

+2 this week 36 Trust /100

Last scanned (20 hours ago)

Scores higher than 37% of OCI servers

Category Finance and Payments

Trust breakdown (7 categories)

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 Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
Provenance & Transparency32
Schema Quality & AI Usability63
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1615 tokens (~269/item across 6 items; 6 tools + 0 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 Management12
  • Stability check failed: the tool surface changed between v0.1.7 and v0.1.11: 4 tool removals, 0 breaking changes, 1 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Changelog

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 9 to 12.

  • 2 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 2 to 6.

  • 28 Oct 26 −1
    • Schema quality: 204 → 269 ▼ functional
    • Package version: v0.1.10 → v0.1.11 functional
  • 24 Oct 26 −3
    • Stability: 0.17 → fail ▼ security
    • Schema quality: 146 → 204 ▼ functional
    • Package version: v0.1.9 → v0.1.10 functional
  • 23 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Oct 26 0
    • Package version: v0.1.7 → v0.1.9 functional
  • 18 Oct 26 36

    First indexed and scored.

Diagnostics

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 4 Nov 2026 · Analysed oci/ghcr.io/dv1-321/scalpstream-mcp@v0.1.11

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 6 exposed · ~1,489 tokens

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 →

Tool Tokens
air_quality ~172

Current US AQI and pollutant breakdown for any coordinates worldwide, an EPA-based verdict on whether it is safe to exercise outdoors, and the cleanest contiguous window in the forecast ahead for a session of a given length. Modelled data (Copernicus CAMS), not a sensor at the exact spot.

NameTypeReqDescription
durationnumber–How long you want to be outside, in hours; the window returned is a contiguous block this long. Default 1, maximum 12.
hoursnumber–How far ahead to search for a clean window, in hours. Default 24, maximum 168.
latnumberyesLatitude in decimal degrees.
lonnumberyesLongitude in decimal degrees.
placestring–Optional label for the location, used in the summary text.
NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–Current AQI and pollutant readings, the EPA activity verdict, and the cleanest contiguous window in the forecast ahead.
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

border_crossings ~230

Ranks US ports of entry by ALL-IN time — the drive there plus the current CBP wait once there — for passenger, commercial or pedestrian traffic, honouring which lanes the traveller may actually use. The nearest crossing is frequently not the fastest. Live CBP data across all 85 US ports of entry.

NameTypeReqDescription
lanesstring–Comma-separated lanes the traveller is eligible for, e.g. 'standard,SENTRI/NEXUS,Ready,FAST'. Defaults to standard only — trusted-traveller lanes are opt-in, since claiming one the traveller cannot u…
latnumberyesLatitude of the starting point, decimal degrees.
limitnumber–How many crossings to return. Default 5.
lonnumberyesLongitude of the starting point, decimal degrees.
placestring–Optional label for the starting point, used in the summary text.
radiusnumber–Limit the search to crossings within this many km. 0 or omitted means no limit.
vehiclestring–Traffic type.
NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–Ports of entry ranked by all-in time, each with the drive time, the current CBP wait, the lanes used and the port identity.
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

cheapest_fuel ~210

Cheapest fuel for a location and grade. Station-level pricing where governments publish open data (Spain, France, Italy); official regional averages for the US via EIA. With smart=true the ranking weighs the pump price against the fuel and time spent on the detour, so the cheapest sign is not always the cheapest tank.

NameTypeReqDescription
countrystringyesISO-3166 alpha-2 country code. ES/FR/IT give station-level prices; US gives a regional average.
gradestring–Fuel grade.
latnumber–Latitude in decimal degrees. Required for station-level countries (ES/FR/IT).
lonnumber–Longitude in decimal degrees. Required for station-level countries.
regionstring–US state code, e.g. CA. Used instead of lat/lon when country=US.
smartboolean–Rank by all-in cost (pump price plus the fuel and time of the detour) rather than pump price alone.
NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–Ranked fuel prices for the requested country and grade, with station or region identity, the price, and its observation date.
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

payment_status ~43

Reports whether paid calls are enabled, how much this session has spent, the price per call, and which payment rails the services accept. Makes no network request and costs nothing.

Input schema present but exposes no named parameters.

NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–Whether paid mode is enabled, confirmed and unconfirmed spend, the number of paid calls, the price per call, the accepted rails, and the custody position.
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

product_recalls ~267

Active US recalls for a product, brand, ingredient or vehicle, searching FDA food/drug/medical-device enforcement, NHTSA vehicle safety campaigns and CPSC consumer product recalls in one query. Severity is normalised across all three regulators onto CRITICAL/SERIOUS/MODERATE/LOW — they grade differently, and the basis for each rating is returned so it can be checked. Includes the recalling firm, hazard, remedy, and the lot numbers and UPCs needed to tell whether a specific unit is affected. Returns ACTIVE recalls by default: a product name can match hundreds of historical recalls and only a handful of open ones. If an agency cannot be reached the response says so and sets complete=false — an incomplete lookup is never an all-clear.

NameTypeReqDescription
include_endedboolean–Also return terminated recalls as history. Off by default; they are rarely what was meant.
limitnumber–Max recalls per list. Default 10.
makestring–Vehicle make. Requires model and year together.
modelstring–Vehicle model.
productstring–Product, brand or ingredient, e.g. 'infant formula'. Matched as a phrase, so keep it short and specific.
yearnumber–Vehicle model year.
NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–Active (and optionally ended) recalls across FDA, NHTSA and CPSC with normalised severity, hazard, remedy, lot numbers, and a `complete` flag that is false when an agency could not be reached.
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

wash_sale_check ~567

Applies the US wash-sale rule (IRC section 1091) to the user's OWN trades, across taxable, IRA and spouse accounts together, and answers a pre-trade question: check=buy asks whether buying `symbol` on date `on` would disallow a loss already taken, and returns the disallowed amount, which sale it comes from and the first safe rebuy date; check=sell asks whether selling `quantity` shares of `symbol` from `account` at a loss on `on` is already washed by a purchase in the 30 days before. Leave check out for the ledger alone: every determination, every sale with realized/disallowed/allowed and short/long term, every open lot's adjusted basis and holding date, and the year's totals. A purchase in an IRA loses the loss permanently and the answer says so. The trades are sent in the request and processed in memory only; the service stores and logs nothing. Everything returned is a rule calculation on the trades given, in sentences that state the rule and never recommend a trade; it is not tax advice, never computes tax owed, matches the same ticker only (no "substantially identical" judgment) and cannot see trades it was not sent. Relay the statement and the disclaimer verbatim.

NameTypeReqDescription
accountstring–check=sell: the account the shares would be sold from, as named in trades. Required with check=sell.
account_typestring–check=buy: where the purchase would be. A purchase in an IRA disallows the loss permanently. Default taxable.
checkstring–The pre-trade question. Omit for the ledger alone.
onstring–The date of the proposed trade, YYYY-MM-DD. Default: today.
quantitynumber–check=sell: how many shares would be sold. Required with check=sell.
symbolstring–The ticker the question is about, as it appears in trades. Required with check.
tradesstringyesThe user's trades, one per row: account,account_type,date,symbol,kind,quantity,price[,fees], rows separated by ';' (account_type: taxable, trad_ira, roth_ira, spouse_taxable, spouse_ira; kind: buy, s…
yearnumber–The tax year to total. Default: the year of `on` with a check, otherwise the year of the latest trade.
NameTypeReqDescription
completebooleanyesWhether `data` is the full dataset this tool describes.
dataobject–The wash-sale calculation on the trades sent: `check` (the answer, with `statement`, `safe`, `safe_date`, `max_disallowed`, `permanent`, and the open `windows` or `replacements`), `determinations`, `…
errorstring–Present when even the free preview could not be fetched.
howtostring–Present when paid=false: how to enable paid calls.
notestring––
paidbooleanyesWhether this result was paid for. False means the free preview.
priceobject–Present when paid=false: the seller's quoted terms.
reasonstring–Present when paid=false: why payment did not happen.
sourcestringyesThe exact URL the data came from.

No examples provided.

Install

How do I install the ScalpStream Data MCP server?

ScalpStream Data runs locally as a container image, launched with docker run --rm -i -e EVM_BASE_PRIVATE_KEY -e SCALPMCP_MAX_PRICE_USD -e SCALPMCP_BUDGET_USD ghcr.io/dv1-321/scalpstream-mcp:v0.1.11. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/dv1-321/scalpstream-mcp

# add to Claude Code
claude mcp add dv1-321-scalpstream-mcp -- docker run --rm -i -e EVM_BASE_PRIVATE_KEY -e SCALPMCP_MAX_PRICE_USD -e SCALPMCP_BUDGET_USD ghcr.io/dv1-321/scalpstream-mcp:v0.1.11

This image reads EVM_BASE_PRIVATE_KEY, SCALPMCP_MAX_PRICE_USD and SCALPMCP_BUDGET_USD. Set them in your client's env block for this server; docker run -e passes each one through to the container.

Common questions

What is the ScalpStream Data MCP server?

ScalpStream Data is an MCP server listed in the public MCP registry as io.github.DV1-321/scalpstream-mcp. Pay-per-call air quality, US product recalls, border waits and cheapest fuel for AI agents via x402. This page covers its container image (ghcr.io/dv1-321/scalpstream-mcp).

Is the ScalpStream Data MCP server safe to use?

ScalpStream Data scores 36 out of 100 on VerifyMCP. 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 ScalpStream Data MCP server expose?

ScalpStream Data exposes 6 tools: cheapest_fuel, air_quality, border_crossings, product_recalls, wash_sale_check, payment_status. Their descriptions and schemas cost roughly 1,489 tokens of context every time the server is loaded.

Is the ScalpStream Data MCP server still maintained?

ScalpStream Data is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.