MCP servers › com.cultmath › decision-briefs
MCP server · registry snapshot 2026-11-15 · last tested 2026-11-18
decision-briefs MCP server
Registry name com.cultmath/decision-briefs
CULT+MATH Decision Briefs — the publisher's title
by cultmath.com · domain (the registry's namespace rule)Website ↗
Odds and forecasts on the numbers executives plan against, plus free studies and Decision Briefs. — the publisher's description
Summary
com.cultmath/decision-briefs is a remote MCP server listed in the official MCP registry at version 1.3.0, under the namespace of the domain cultmath.com. On 2026-11-18 ProtocolProbe connected to it in read-only mode and read its inventory: 67 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 67
- Last tested
- 2026-11-18
Tool list size
39,957 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (67 tools). Counted with Anthropic's token counter on 2026-11-18, from the tool list we read on 2026-11-18. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-18 (cultmath.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.3.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-18
- Mode
- read-only (no tool calls)
- Latest version
- 1.3.0, published 2026-11-14 (registry, as of the 2026-11-15 snapshot)
- First listed version
- 2026-11-07 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-11-07 to 2026-11-14; 2 in the 90 days before the 2026-11-15 snapshot.(versions still listed in the registry only)
Most recent 2 versions
1.3.0· 2026-11-141.1.0· 2026-11-07
- Registry data
- snapshot 2026-11-15
- Package and repository
- checked 2026-11-15
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
Version 1.1.0 (published 2026-11-07) → 1.3.0 (published 2026-11-14), between the registry lists of 2026-11-14 and 2026-11-15.
No release note: the registry entry links no GitHub repository.
Source: the official MCP Registry list on 2026-11-14 and on 2026-11-15; release notes from the GitHub Releases API, checked 2026-11-15.
What it is
What does this server offer?
Observed inventoryNone of its 67 tools are described as changing anything. For 67 the reading was uncertain, so no mark is shown.
- list_decision_briefs
“List the CULT+MATH Decision Briefs: who each is written for, its headline finding, price, page and payment link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
categorystring“Optional filter, e.g.”
- get_decision_brief
“Everything public about one brief: the decisions it covers (six or more) with the evidence line for each, pages, edition, price, sample pages, free answers, guarantee, license and payment link.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired“Brief id from list_decision_briefs, e.g.”
- search_cultmath
“Search the free CULT+MATH studies and answers (and the briefs) by keywords.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
querystringrequired“Keywords, e.g.”kindstring“Restrict results.”limitinteger“Default 5.”
- list_decisionson 10 other servers
“The single decisions inside the briefs (six or more per brief), each with who owns it, who contests it, and the public evidence line.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
brief_idstring“Optional: only this brief, e.g.”querystring“Optional keywords to filter by.”
- buy_decision_evidence
“Starts a Stripe checkout for the full evidence behind one decision: sourced and dated figures, what would flip the answer, and the brief's stated limits.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
decision_idstringrequired“From list_decisions, e.g.”
- get_decision_evidence
“Returns the full evidence for one decision once it is paid for.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
decision_idstringrequired“The id from list_decisions, e.g.”session_idstringrequired“A Stripe Checkout Session id (cs_live_...).”
- get_documenton 82 other servers
“Read every published finding (question and answer) of one CULT+MATH study or answer page, with its date, license, citation line and related brief.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
urlstringrequired“A cultmath.com/research/...”
- tell_cultmath
“Free.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
reasonstringrequired“The main reason the run was not bought.”runstring“Optional: the run_* tool it was about, e.g.”
- list_standardson 9 other servers
“Free.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
modulestring“Optional: only the standards in one module.”
- get_standardon 13 other servers
“Free.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired“The standard's id, e.g.”
- run_filing_trend
“Use when the user asks whether a risk, technology or theme is spreading through public companies, or whether companies now treat it as material.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
phrasestringrequired“The phrase to count, without quote marks, e.g.”startinteger“First year (2001 onward).”endinteger“Last year, not in the future.”
- run_regulatory_trend
“Use when the user asks whether rules are coming on a topic, or how much federal rule-making mentions it, optionally for one agency.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
phrasestringrequired“The phrase to count, without quote marks, e.g.”startinteger“First year (1994 onward).”endinteger“Last year, not in the future.”agencystring“Optional: count only this agency's rules.”
Show 55 more tools
- run_spend_trend
“Use when the user asks whether federal money backs a market, technology or policy, or wants evidence beyond announcements.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
phrasestringrequired“The phrase to measure, without quote marks.”startinteger“First federal fiscal year.”endinteger“Last fiscal year, not after the current one.”
- run_triangulation
“Use when the user needs to know whether a trend is substantive or hype before acting on it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
phrasestringrequired“The phrase to measure, without quote marks.”startinteger“First year.”endinteger“Last year.”
- run_peer_benchmark
“Use when the user names a public company and asks how its growth, margin, R&D or marketing spend compares with competitors.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 3 required
tickerstringrequired“The company.”peersstringrequired“2-6 peer tickers from the same list, comma-separated, e.g.”metricstringrequired“What to compare, from each company's latest 10-K: revenue_growth (revenue growth), gross_margin (gross margin), rd_intensity (R&D as a share of revenue), sm_in…”
- run_ai_visibility
“Use when the user asks whether their brand or website shows up in AI answers, or who AI assistants cite instead.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
questionstringrequired“The question a buyer would ask an AI assistant.”domainstringrequired“The domain to look for, e.g.”
- run_ai_visibility_quick
“Use when the user asks whether their brand or website shows up in AI answers and a quick read is enough.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
questionstringrequired“The question a buyer would ask an AI assistant.”domainstringrequired“The domain to look for, e.g.”
- run_disclosure_check
“Use when the user asks whether any company, or which of a named set of competitors, now reports a figure (a franchise share, ARPU, a retention rate, a concentration, a multiple), or whether a public …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
phrasestringrequired“The phrase to measure, without quote marks.”peersstring“Optional: 2-10 tickers, comma-separated, from: PEP, KO, K, POST, KDP, CELH, UTZ, HRL, GIS, KHC, CAG, CPB, HSY, MDLZ, SJM, CLX, CL, CHD, PG, SMPL, BRBR, MSFT, E…”formstring“Filing type.”startinteger“First year.”endinteger“Last year.”
- run_regulatory_clock
“Use when the user asks whether a U.S.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
phrasestringrequired“The phrase to measure, without quote marks.”agencystring“Optional: one agency only.”
- run_deal_activity
“Use when the user asks about M&A activity, deal flow or consolidation in a sector, whether now is a good time to buy or sell a company in it, or who the active acquirers are.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
sectorstring“A named sector, with its phrase and industry codes set for you.”phrasestring“Your own sector phrase, without quote marks, if no named sector fits.”sicstring“Optional, with phrase: four-digit SIC codes for the cross-check, comma-separated, e.g.”quartersinteger“How many quarters, ending with the last complete one.”
- run_demand_check
“Use when the user asks whether interest in a product, category or trend is really growing, or wants to know if a rise in search is more than noise before investing in it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
phrasestringrequired“The category as people search for it, e.g.”alsostring“Optional: up to 4 more keywords for the same category, comma-separated.”
- run_answer_share
“Use when the user asks which brands or websites AI assistants rely on for their category, who they are competing with in AI answers, or whether any source dominates.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 2 required
q1stringrequired“A question a buyer in the category would ask an AI assistant.”q2stringrequired“A second, different buyer question.”q3string“Optional third question.”domainstring“Optional: your domain, e.g.”
- run_answer_share_quick
“Use when the user asks which brands or websites AI assistants rely on for their category and a quick read is enough.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
q1stringrequired“A question a buyer in the category would ask an AI assistant.”q2stringrequired“A second, different buyer question.”domainstring“Optional: your domain, e.g.”
- run_share_of_search
“Use when the user asks who they really compete with, whether a competitor is gaining on them, or how their brand interest compares with rivals.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
brandstringrequired“Your brand as people search for it.”rivalsstringrequired“2-6 competing brands, comma-separated.”
- run_premium_check
“Use when the user asks whether their price premium is holding, whether customers are trading down, or whether a price rise is hurting demand.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
brandstringrequired“One brand, spelled as people type it into Google, e.g.”
- run_angle_demand
“Use when the user is choosing a positioning, a message or a campaign angle and asks which benefit or reason to buy matters most to buyers, or which is gaining.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
categorystringrequired“The category as people search for it, e.g.”anglesstringrequired“2-6 reasons to buy, comma-separated, e.g.”
- run_channel_mix
“Use when the user is planning go-to-market or channel strategy and asks where buyers look, whether to prioritise retail, review sites, their own site or communities, or who controls the first page fo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
6 inputs, 1 required
q1stringrequired“A search a buyer would make, e.g.”q2string“Optional second search.”q3string“Optional third search.”brand_domainsstring“Optional: the category's brand sites, comma-separated, so they are classed as brands.”retailer_domainsstring“Optional: specialist retailers to class as retailers.”media_domainsstring“Optional: specialist review or media sites to class as media.”
- run_claim_check
“Use when the user is choosing a positioning, a tagline or a message and asks whether competitors already say it, whether a claim is crowded or open, or who has moved onto it recently.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
claimstringrequired“The claim as a buyer would read it, e.g.”variantsstring“Optional: up to 3 other wordings, comma-separated.”sitesstringrequired“3-5 competitor domains, comma-separated.”
- run_fad_check
“Use when the user is writing a creative or campaign brief, or weighing a trend, and asks whether a moment, ingredient, format or cultural theme is a lasting shift or a fad that has peaked.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
termstringrequired“The moment as people search for it, e.g.”articlestringrequired“The English Wikipedia article on the same subject, e.g.”
- run_revenue_mix
“Use when the user names a public company and asks how its revenue splits (by platform, revenue type, channel, product or region) or whether its mix is shifting, for example toward mobile, live servic…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
tickerstringrequired“The company.”
- run_launch_lift
“Use when the user asks whether a line extension, spin-off, sequel, collaboration or new product lifted interest in the parent brand or show, or is weighing a launch on the promise of a halo.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
parentstringrequired“The parent brand or show as people search for it, e.g.”launchstringrequired“The launch or premiere month, YYYY-MM, 2020-04 or later and finished.”articlestring“Optional: the English Wikipedia article on the parent, e.g.”
- run_comment_themes
“Use when the user wants to know what viewers raise under a trailer, launch video, ad or review on YouTube, for example whether they talk about price, a feature or a complaint.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
videosstringrequired“1-5 YouTube video IDs (the 11 characters after v= in the link), comma-separated.”themesstringrequired“1-8 words or short phrases to count, comma-separated, e.g.”
- run_customer_concentration
“Use when the user asks how much of a public company's revenue comes from one retailer or customer (for example Walmart), or is weighing the risk of selling through a dominant buyer.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
tickerstringrequired“The company.”
- run_write_downs
“Use when the user asks whether a company has impaired a brand or an acquisition, is preparing to sell a brand to a strategic buyer, or wants to know how acquirers have valued past deals.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
tickerstringrequired“The company.”
- run_cost_squeeze
“Use when the user asks whether a commodity shock (cocoa, coffee, sugar, wheat, corn, beef, aluminum, crude oil) has squeezed a public company's margin, whether it passed the cost through, or what a p…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
tickerstringrequired“The company.”commoditystringrequired“The input, as an IMF global price.”
- run_trade_concentration
“Use when the user asks whether supply of a product has really diversified, how exposed US imports are to one country, or who gained share after tariffs or reshoring.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 3 required
hsstringrequired“A 4- or 6-digit HS code, e.g.”startintegerrequired“The earlier year.”endintegerrequired“The later year (the latest full year is usually the one before last).”
- run_series_forecast
“Use when the user is setting a plan, budget or inventory for the next year and needs where US retail sales, prices (CPI), employment and wages, industrial production, housing or vehicle sales are hea…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
seriesstringrequired“The FRED series ID, e.g.”
- run_threshold_odds
“Use when the user's plan turns on whether rent, food prices, household energy, wages or retail sales will be above or below a level soon: "what are the chances rent inflation is above 3% in December?…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 3 required
seriesstringrequired“The FRED series ID, e.g.”monthstringrequired“The target month, YYYY-MM, 1 to 3 months after the latest published figure.”yoy_pctnumberrequired“The line: year-on-year change in percent, e.g.”directionstring“Whether you want the odds of being above or below the line.”
- run_effective_duty
“Use when the user is pricing, sourcing or sizing a refund claim and needs the tariff actually paid on a product, not the headline rate: "what duty are we really paying on chips from Malaysia?", "how …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 3 required
hsstringrequired“A 4-, 6- or 10-digit HS code, e.g.”fromstringrequired“The earlier month, YYYY-MM, January 2025 to July 2026.”tostringrequired“The later month, YYYY-MM, after from, up to July 2026.”countriesstring“Optional: up to 5 source countries to show by name, comma-separated, e.g.”
- run_tariff_clock
“Use when the user is timing a sourcing, pricing or comment decision around US tariffs: "is anything new on Section 301 for Vietnam?", "when do the chip tariffs take effect?", "can we still comment on…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
phrasestringrequired“A product, an HTS heading (e.g.”agencystring“Optional: one agency only (ustr, ita, bis, cbp, president).”since_daysinteger“How far back to list recent actions, in days.”
- run_city_profile
“Use when the user is weighing a housing, zoning, development or site decision for a US city, or checking a claim about one: "is Boise building enough housing?", "how fast has rent risen in St.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
statestringrequired“Two-letter US state code, e.g.”placestringrequired“The city name as people write it, e.g.”
- run_deal_comps
“Use when the user is underwriting an entry or exit multiple, pricing an acquisition, or asks what similar companies sold for: "what EBITDA multiples are cybersecurity deals getting?", "what did banke…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
sectorstring“A named sector.”phrasestring“Your own sector phrase, without quote marks.”yearsinteger“How many years back to search.”
- run_concentration_benchmark
“Use when the user is pricing customer-concentration risk in a deal or asks whether a target’s reliance on one customer (often Walmart) is unusual: "our target gets 32% from Walmart, is that high for …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
peersstringrequired“2-6 peer tickers, comma-separated, from: PEP, KO, K, POST, KDP, CELH, UTZ, HRL, GIS, KHC, CAG, CPB, HSY, MDLZ, SJM, CLX, CL, CHD, PG, SMPL, BRBR, MSFT, EA, TTW…”tickerstring“Optional: a public company from the same list to place against the peers.”target_sharenumber“Optional: a private target’s largest customer as a percent of revenue, from its own books.”
- run_demand_durability
“Use when the user is checking a consumer target’s growth story in diligence, or asks whether a brand’s momentum will last: "is Celsius still gaining on Monster?", "is this brand a fad?".”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 3 required
brandstringrequired“The brand as people search for it.”rivalsstringrequired“2-6 competing brands, comma-separated.”articlestringrequired“The English Wikipedia article on the brand or its company, e.g.”
- run_merger_review
“Use when the user is setting regulatory-risk terms for a deal (outside date, reverse break fee, divestiture commitments) or asks whether regulators have blocked or conditioned deals in a sector: "hav…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
phrasestringrequired“A sector or product, e.g.”since_yearinteger“First year to count.”
- run_private_raises
“Use when the user asks where private capital is going, how crowded an industry is with funded competitors, or whether fund-raising is picking up: "are biotech private raises up this year?", "who rais…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
industrystringrequired“A Form D industry group.”quartersinteger“Quarters to count.”
- run_contractor_revenue
“Use when the user is diligencing a government-services or defense target, sizing recompete risk, or asks how dependent a company is on one agency: "how much does this contractor get from the Army?", …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
recipientstringrequired“The company as it appears on federal awards.”yearsinteger“Fiscal years to cover, ending with the current one.”
- run_ai_readiness
“Use when the user asks why AI assistants do not cite their site, whether their site is "AI friendly", or whether they block ChatGPT, Claude or Perplexity: "is our robots.txt blocking AI?", "do we nee…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
domainstringrequired“A public domain name, e.g.”
- run_search_vs_ai
“Use when the user is deciding between SEO and AI-visibility (GEO) work, or asks whether ranking in Google gets them cited by ChatGPT, Claude, Gemini or Perplexity: "we rank #2 on Google, why don’t AI…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
questionstringrequired“The question as a buyer would type or ask it.”domainstring“Optional: your domain, to see where it stands in both.”
- run_ai_brand_check
“Use when the user asks what ChatGPT, Claude, Gemini or Perplexity say about their company, or whether assistants get their facts right: "does ChatGPT know where we are based?", "do AI assistants know…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
brandstringrequired“The brand as buyers say it.”factsobjectrequired“Label and value pairs, e.g.”
- run_trial_pipeline
“Use when the user is sizing a therapeutic area, diligencing a biotech or medtech target, or asks how many companies are running trials for a condition: "how crowded is the obesity pipeline?", "who sp…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
conditionstringrequired“A disease or condition, e.g.”yearsinteger“Complete calendar years to cover, ending last year.”
- run_device_clearances
“Use when the user is sizing competition in a medical device category, diligencing a medtech target, or asks who is bringing devices to market: "how many pulse oximeters got 510(k) clearance?", "which…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
product_codestring“The FDA three-letter product code, e.g.”devicestring“A device phrase matched against device names, e.g.”yearsinteger“Complete calendar years to cover, ending last year.”
- run_recall_watch
“Use when the user is weighing quality or supplier risk in a food, drug or device category, diligencing a manufacturer, or asks about recall history: "are ice cream recalls rising?", "who recalls the …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
categorystringrequired“Which FDA enforcement report to read.”phrasestringrequired“Matched against product descriptions, e.g.”yearsinteger“Complete calendar years to cover, ending last year.”
- run_incentive_tracts
“Use when the user is structuring a real estate or business investment and asks about tax-advantaged capital for a specific site: "is this address in an Opportunity Zone?", "will it still be one in 20…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
addressstring“One US street address.”addressesarray“Up to 10 US street addresses, for a portfolio.”
- run_trade_area
“Use when the user is choosing or underwriting a site for a store, restaurant, clinic, school or property and asks about the catchment: "how many people live within 3 miles?", "what is household incom…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
addressstring“A US street address.”latnumber“Latitude in decimal degrees, with lon.”lonnumber“Longitude in decimal degrees, with lat.”radius_milesnumber“Radius in miles.”
- run_parcel_mix
“Use when the user is screening a site in Harris County, Texas (Houston) for development, investment or lending and asks what surrounds it: "what is around this lot?", "how much vacant land is nearby?…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
addressstring“A US street address.”latnumber“Latitude in decimal degrees, with lon.”lonnumber“Longitude in decimal degrees, with lat.”radius_milesnumber“Radius in miles.”
- run_audience_size
“Use when the user is defining or sizing a consumer audience or checking a TAM claim: "how many college-educated 25-34 year olds are in the US?", "how many homeowner households in Texas earn over $150…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
15 inputs
unitstring“Count people or households.”statestring“Two-letter US state code, or US.”pumasarray“Optional: up to 10 PUMA codes within the state.”age_mininteger“Youngest age, in years.”age_maxinteger“Oldest age, in years.”sexstring“Optional: one sex.”household_income_mininteger“Household income floor, dollars a year.”household_income_maxinteger“Household income ceiling, dollars a year.”personal_income_mininteger“Personal income floor, dollars a year.”personal_income_maxinteger“Personal income ceiling, dollars a year.”educationstring“Minimum education.”employedboolean“true to count only the employed.”tenurestring“Owner or renter households.”childrenboolean“true: children at home; false: none.”occupationsarray“Census occupation codes (OCCP), up to 5.”
- run_audience_map
“Use when the user is choosing where to target, open, or send sales or media: "which Texas counties have the most high-income young households?", "which Harris County tracts concentrate households 65 …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
statestringrequired“Two-letter US state code.”countystring“Optional three-digit county FIPS code: ranks its tracts instead of the state’s counties.”age_bandsarray“Householder age bands.”income_mininteger“Household income floor, one of 0, 10000, 15000, 20000, 25000, 30000, 35000, 40000, 45000, 50000, 60000, 75000, 100000, 125000, 150000, 200000.”income_maxinteger“Optional household income ceiling, at the same edges.”
- run_business_universe
“Use when the user is sizing a B2B market in firms, planning a roll-up or territory, or asks how many companies of a kind exist: "how many CPA firms are in Texas?", "how many restaurants are in Harris…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
naicsstringrequired“NAICS industry code, 2-6 digits.”statestring“Two-letter US state code, or US.”countystring“Three-digit county FIPS code, with state.”cbsastring“Five-digit metro area code, e.g.”zipstring“Five-digit ZIP code (employer data only).”
- run_buyer_roles
“Use when the user is sizing a B2B buyer persona or a hiring market: "how many marketing managers are in Houston?", "how many accountants work in Texas and what do they earn?".”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
socstringrequired“Six-digit SOC occupation code, e.g.”statestring“Two-letter US state code, or US.”cbsastring“Five-digit metro area code, e.g.”
- run_wallet_size
“Use when the user is sizing a consumer market in dollars or comparing spend across groups: "how big is the US restaurant market by household income?", "which age group spends most on pets?".”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
itemstringrequired“Spending category (CE item code).”bystring“How to split households.”
- run_news_pulse
“Currently switched off: it answers "not available" and charges nothing.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
querystringrequired“A phrase, matched exactly, e.g.”daysinteger“Days back from today.”
- run_news_share_of_voice
“Currently switched off: it answers "not available" and charges nothing.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
namesarrayrequired“2-3 names to compare.”daysinteger“Days back from today.”
- run_social_pulse
“Use when the user is listening for discussion of a brand, product, launch or category among technical and early-adopter audiences: "is anyone talking about our launch?", "did this topic spike this mo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
querystringrequired“A phrase, matched exactly.”daysinteger“Days back from today.”
- run_social_share_of_voice
“Use when the user is comparing community attention across competitors or products: "do developers talk about us or them more?", "which tool gets more discussion?".”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
namesarrayrequired“2-4 names to compare.”daysinteger“Days back from today.”
- run_topic_views
“Use when the user is a creator, creator manager or brand team planning content on a subject and asks which angle gets watched: "which GTA 6 topics are pulling views right now?", "do trailer videos be…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
querystringrequired“The subject, as people search it, e.g.”topicsarrayrequired“2-4 title words or short phrases to split the videos by, e.g.”daysinteger“Days back from today.”
- run_channel_benchmark
“Use when the user is a creator or brand-partnership lead comparing channels: "how does my channel stack up against these three?", "who posts more Shorts and does it pay?", "which creator should we sp…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
channelsarrayrequired“2-5 channels, each an @handle (e.g.”daysinteger“Days back from today.”termsarray“Optional: up to 4 title words to compare titles with and without them.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-18.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 180
- Tools with a description
- 100% of 67
- Typical description length
- 1,087 characters
The tool set
Counted from the listing
- Tools
- 67
- Size of the list
- about 46,542 tokens for an agent to load (characters ÷ 4)
- Naming
- 67 of 67 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 67 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-18 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://cultmath.com/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"decision-briefs": {
"url": "https://cultmath.com/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"decision-briefs": {
"type": "http",
"url": "https://cultmath.com/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"decision-briefs","type":"http","url":"https://cultmath.com/mcp"}'Claude Code
claude mcp add --transport http decision-briefs https://cultmath.com/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"decision-briefs": {
"type": "streamableHttp",
"url": "https://cultmath.com/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"decision-briefs": {
"httpUrl": "https://cultmath.com/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.decision-briefs] url = "https://cultmath.com/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"decision-briefs": {
"url": "https://cultmath.com/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://cultmath.com/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-15. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-15. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-15. Source: read 2026-11-15.
- Cline marketplace. Not in the Cline marketplace on 2026-11-15. Source: read 2026-11-15.
Own host
- security.txt. security.txt found at https://cultmath.com/.well-known/security.txt (Contact given; expires 2027-05-04). Source: cultmath.com/.well-known/security.txt · read 2026-11-15.
- A2A agent card. An A2A agent card is published at https://cultmath.com/.well-known/agent-card.json (name, skills, supportedInterfaces). Source: cultmath.com/.well-known/agent-card.json · read 2026-11-15.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint cultmath.com/mcp | Session opened | matches | our test · 2026-11-18 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-18 |
Tool list changes
Our reads compared · no tool calledHosted endpoint cultmath.com/mcp
2 of 2 comparisons between consecutive reads showed a change (3 reads, 2026-11-08 to 2026-11-18; versions 1.1.0 to 1.3.0).
Last change seen between our reads on 2026-11-15 (version 1.3.0) and 2026-11-18 (version 1.3.0). Changed without a new version: both reads list version 1.3.0.
Added (32) (25 shown):
get_standardlist_standardsrun_ai_brand_checkrun_ai_readinessrun_audience_maprun_audience_sizerun_business_universerun_buyer_rolesrun_channel_benchmarkrun_city_profilerun_concentration_benchmarkrun_contractor_revenuerun_deal_compsrun_demand_durabilityrun_device_clearancesrun_effective_dutyrun_incentive_tractsrun_merger_reviewrun_news_pulserun_news_share_of_voicerun_parcel_mixrun_private_raisesrun_recall_watchrun_search_vs_airun_social_pulseand 7 more.
Changed (30) (25 shown):
get_decision_brief: descriptionlist_decisions: descriptionrun_ai_visibility: descriptionrun_ai_visibility_quick: descriptionrun_angle_demand: descriptionrun_answer_share: descriptionrun_answer_share_quick: descriptionrun_channel_mix: descriptionrun_claim_check: descriptionrun_comment_themes: descriptionrun_cost_squeeze: descriptionrun_customer_concentration: descriptionrun_deal_activity: descriptionrun_demand_check: descriptionrun_disclosure_check: descriptionrun_fad_check: descriptionrun_filing_trend: descriptionrun_launch_lift: descriptionrun_peer_benchmark: descriptionrun_premium_check: descriptionrun_regulatory_clock: descriptionrun_regulatory_trend: descriptionrun_revenue_mix: descriptionrun_series_forecast: descriptionrun_share_of_search: descriptionand 5 more.
Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-18 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-15. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about com.cultmath/decision-briefs
Answered from the data aboveWho publishes com.cultmath/decision-briefs?
The registry ties the namespace com.cultmath to the domain cultmath.com; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does com.cultmath/decision-briefs need an API key or sign-in?
It opened a session without any credential on 2026-11-18. The registry entry declares no required credential; no declaration is not a guarantee.
Has com.cultmath/decision-briefs been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (no operator permission)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-18, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,531 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 67 tools, 0 resources, 0 prompts.
- 5,287 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “com.cultmath/decision-briefs: MCP server record.” Data checked 2026-11-18. https://protocolprobe.com/mcp/servers/com.cultmath/decision-briefs
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/com.cultmath/decision-briefs)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology