Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions
Directory / CULT+MATH Decision Briefs
CULT+MATH Decision Briefs
by cultmath.com · https://cultmath.com/mcp
Sourced, dated evidence for executive decisions: free studies, $495 briefs, paid SEC filing runs.
12 of 12 checks · 7 Nov 2026
At a glance
- Runs where
- On their server. What you send to it goes to them.
- What you need
- Nothing: it answered without a login
- Tools
- 24 tools
- Its own safety labels
- 23 read-only, 1 labeled as changing things
- Memory it takes
- About 7,500 tokens of your AI's memory, just for its tool descriptions
- Largest answer
- About 55 KB in our test
- Tools that look alike
- 1 pair of tools with nearly the same description, so the AI may pick the wrong one
- Speed
- Average answer in our test: 71 ms
Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 7 Nov 2026.
Is CULT+MATH Decision Briefs MCP server safe?
- None of the hidden-instruction wordings we know were found in its 24 tool descriptions.
- Its error messages showed no secrets or internal details.
- 23 of its 24 tools are labeled read-only; the others may change or send things.
- Overall it scored 80/100 on 7 Nov 2026.
A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.
What this test does not check
- Its source code and packages.
- What a tool quietly does behind the scenes, such as writing a file or calling another service.
- Instructions hidden inside live tool answers. We only look for those in tool descriptions.
- Hidden instructions worded in a way our list doesn't know yet.
- Tools that could change something. Those are read, never run.
What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection
Known security advisories
It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.
What it can do
24 tools, in the server's own words.
list_decision_briefsread-onlyList the CULT+MATH Decision Briefs: who each is written for, its headline finding, price, page and payment link.
get_decision_briefread-onlyEverything public about one brief: the six decisions it covers with the evidence line for each, pages, edition, price, sample pages, free answers, guarantee, l…
search_cultmathread-onlySearch the free CULT+MATH studies and answers (and the briefs) by keywords.
list_decisionsread-onlyThe 54 decisions inside the briefs (six per brief), each with who owns it, who contests it, and the public evidence line.
buy_decision_evidenceStarts 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.
get_decision_evidenceread-onlyReturns the full evidence for one decision once it is paid for.
get_documentread-onlyEvery published finding (question and answer) of one CULT+MATH study or answer page, with its date, license, citation line and related brief.
run_filing_trendread-onlyUse when the user asks whether a risk, technology or theme is spreading through public companies, or whether companies now treat it as material.
run_regulatory_trendread-onlyUse when the user asks whether rules are coming on a topic, or how much federal rule-making mentions it, optionally for one agency.
run_spend_trendread-onlyUse when the user asks whether federal money backs a market, technology or policy, or wants evidence beyond announcements.
run_triangulationread-onlyUse when the user needs to know whether a trend is substantive or hype before acting on it.
run_peer_benchmarkread-onlyUse when the user names a public company and asks how its growth, margin, R&D or marketing spend compares with competitors.
run_ai_visibilityread-onlyUse when the user asks whether their brand or website shows up in AI answers, or who AI assistants cite instead.
run_disclosure_checkread-onlyUse 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 concentr…
run_regulatory_clockread-onlyUse when the user asks whether a U.S.
run_deal_activityread-onlyUse 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…
run_demand_checkread-onlyUse 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 inves…
run_answer_shareread-onlyUse 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 domi…
run_share_of_searchread-onlyUse when the user asks who they really compete with, whether a competitor is gaining on them, or how their brand interest compares with rivals.
run_premium_checkread-onlyUse when the user asks whether their price premium is holding, whether customers are trading down, or whether a price rise is hurting demand.
run_angle_demandread-onlyUse 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.
run_channel_mixread-onlyUse 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 commun…
run_claim_checkread-onlyUse 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…
run_fad_checkread-onlyUse 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 sh…
Test results
Safe mode: only tools labeled read-only were run. How the test works
- !Ready for the newest MCP versionnote
1 warning
- !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
- !Every tool is describednote
3 warnings
- !get_decision_evidence: Inputs with no description: decision_id
- !run_peer_benchmark: Inputs with no description: metric
- !run_ai_visibility and run_answer_share have nearly the same description (60% of their words are shared; the only difference: "show", "instead", "web" vs "rely", "category", "they"), so an AI may not know which to pick
- !Tools are labeled safe or dangerousnote
17 warnings
- !run_filing_trend: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_regulatory_trend: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_spend_trend: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_triangulation: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_peer_benchmark: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_ai_visibility: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_disclosure_check: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- !run_regulatory_clock: Labeled read-only, but its name starts with "run" and its description says "charges". Worth double-checking the label, since AI apps trust it.
- and 9 more
- !Bad inputs give a clean errornote
4 warnings
- !list_decision_briefs: Accepted wrong type for "category" without complaining
- !search_cultmath: Accepted missing required input "query" without complaining
- !search_cultmath: Accepted wrong type for "query" without complaining
- !list_decisions: Accepted wrong type for "brief_id" without complaining
- and 6 more
- ✓ConnectsConnected in 642 mspass
- ✓Lists its toolsFound 24 toolspass
- ✓No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.pass
- ✓Tools work with good inputspass
All good
- ✓list_decision_briefs: Worked (75 ms)
- ✓get_decision_brief: Answered with an error, probably because of our sample input: { "error": "No brief \"test\". Valid ids: cybersecurity, entertainment-games, entertainment-streaming, entertainment-studios, cpg-brand-man…
- ✓search_cultmath: Worked (78 ms)
- ✓list_decisions: Worked (69 ms)
- ✓get_decision_evidence: Answered with an error, probably because of our sample input: { "error": "Unknown decision_id. Use list_decisions.", "attribution": { "source": "CULT+MATH (cultmath.com), research by Ipalibo Da-Waribok…
- ✓get_document: Answered with an error, probably because of our sample input: { "error": "No study or answer at that URL. Use search_cultmath to find one.", "attribution": { "source": "CULT+MATH (cultmath.com), resear…
- –buy_decision_evidence: Not run: labeled as changing data
- –run_filing_trend: Not run: labeled read-only, but its name starts with "run", which usually means it changes something. Skipped to be safe: if it only reads, a clearer name helps AI apps too, or test again with --owner
- and 16 more
- ✓Tools work togetherpass
5 chains working
- ✓list_decision_briefs → get_decision_brief: get_decision_brief found what list_decision_briefs returned (id = "cybersecurity")
- ✓search_cultmath → get_decision_brief: get_decision_brief found what search_cultmath returned (id = "cpg-brand-manager")
- ✓search_cultmath → get_document: get_document found what search_cultmath returned (url = "https://cultmath.com/answers/calculate-gross-margin-from-se…")
- ✓list_decision_briefs → list_decisions: list_decisions found what list_decision_briefs returned (brief_id = "cybersecurity")
- ✓search_cultmath → list_decisions: list_decisions found what search_cultmath returned (brief_id = "cpg-brand-manager")
- ✓Fast enoughpass
All good
- ✓Connecting took 642 ms
- ✓Listing tools took 216 ms
- ✓Average tool answer: 71 ms
- ✓search_cultmath: Slowest tool: search_cultmath (78 ms)
- ✓No secrets leakedChecked 20 error messages: no secrets or internal detailspass
- ✓Follows MCP best practices (not scored yet)Tool names, safety labels and tool list size follow the MCP guidepass
Test it yourself
Free and open source. Same checks, same score.
npx qamcp-cli https://cultmath.com/mcpShow this score on GitHub
Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.
[](https://qamcp.dev/s/com-cultmath-decision-briefs.html)Score over time
- 7 Nov 202680
One test so far. New tests will show here.
Reviews
Coming soon: reviews from people who use CULT+MATH Decision Briefs, signed in with GitHub, one per person. Reviews never change the score.
QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.
Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works