_ registry / mcp streamable-http · checked 19m ago

cultmath

https://cultmath.com

Registry code: e5712c82184c1261

api record

CULT+MATH publishes Decision Briefs: sourced, dated evidence for one executive decision-space (cybersecurity vendors, games publishers, streaming services, film studios, CPG brand managers, premium CPG founders, mid-market ERP CROs, middle-market PE deal partners, CMOs on AI visibility). $495 each as a PDF, 14-day guarantee. Use search_cultmath to find a free study or answer on a question, get_document to read its findings in full, and list_decision_briefs / get_decision_brief when the user is weighing a decision a brief covers. list_decisions shows the 54 single decisions;…

endpoint
https://cultmath.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is cultmath live?
Yes — it answered the hub's last check (checked 19m ago). It answered 100% of checks over the last 30 days.
Is cultmath free to use?
Yes — the hub reached it with no key and no payment.
What tools does cultmath have?
13 tools: run_regulatory_trend, run_spend_trend, run_triangulation, run_peer_benchmark, run_ai_visibility, get_decision_brief, search_cultmath, get_decision_evidence, ….
Is cultmath safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
292ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 13 tools
2 open 11 never probed 2 of 13 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_decisions open 19m ago

    The 54 decisions inside the briefs (six per brief), each with who owns it, who contests it, and the public evidence line. Use an id with buy_decision_evidence to buy the full evidence for just that decision.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Optional keywords to filter by."
    },
    "brief_id": {
      "type": "string",
      "description": "Optional: only this brief, e.g. \"cpg-premium\"."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • list_decision_briefs open 19m ago

    List the CULT+MATH Decision Briefs: who each is written for, its headline finding, price, page and payment link. Also lists bundles and the custom brief.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Optional filter, e.g. \"CPG\", \"Entertainment\", \"Private equity\"."
    }
  },
  "additionalProperties": false
}
    arguments 10 lines
  • run_regulatory_trend unknown never probed

    A fresh, citable measurement: what share of U.S. federal final and proposed rules mention a phrase, year by year, from the Federal Register, optionally for one agency. The denominator is every final and proposed rule that year; a null control that no document contains must return 0; the stated limits, a run id and a dated citation line come with it. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls. Pairs with run_filing_trend: what regulators write next to what companies tell investors.

    mcp-tool

    {
  "type": "object",
  "required": [
    "phrase"
  ],
  "properties": {
    "end": {
      "type": "integer",
      "description": "Last year, not in the future. Default: this year. At most 10 years per run."
    },
    "start": {
      "type": "integer",
      "minimum": 1994,
      "description": "First year (1994 onward). Default: four years ago."
    },
    "agency": {
      "enum": [
        "fda",
        "usda",
        "ftc",
        "epa",
        "cpsc",
        "fcc",
        "sec",
        "dol",
        "treasury"
      ],
      "type": "string",
      "description": "Optional: count only this agency's rules."
    },
    "phrase": {
      "type": "string",
      "maxLength": 80,
      "minLength": 3,
      "description": "The phrase to count, without quote marks, e.g. \"front-of-package\" or \"PFAS\"."
    }
  },
  "additionalProperties": false
}
    arguments 39 lines
  • run_spend_trend unknown never probed

    A fresh, citable measurement: what share of U.S. federal prime contract obligations match a keyword, by federal fiscal year, from USAspending.gov. The denominator is all prime contract obligations that year; a null control that no award contains must match $0; the stated limits, a run id and a dated citation line come with it. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "phrase"
  ],
  "properties": {
    "end": {
      "type": "integer",
      "description": "Last fiscal year, not after the current one. At most 10."
    },
    "start": {
      "type": "integer",
      "minimum": 2008,
      "description": "First federal fiscal year. Default: four years ago."
    },
    "phrase": {
      "type": "string",
      "maxLength": 80,
      "minLength": 3,
      "description": "The phrase to measure, without quote marks."
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • run_triangulation unknown never probed

    One phrase measured in three independent public sources at once: the share of 10-K filers mentioning it (SEC EDGAR), the share of federal final and proposed rules (Federal Register), and the share of federal contract obligations (USAspending), year by year, each with its own controls, plus the direction of each line and whether they agree. If any source fails its controls the run is unsound. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "phrase"
  ],
  "properties": {
    "end": {
      "type": "integer",
      "description": "Last year. At most 5 years per run."
    },
    "start": {
      "type": "integer",
      "minimum": 2008,
      "description": "First year. Default: four years ago."
    },
    "phrase": {
      "type": "string",
      "maxLength": 80,
      "minLength": 3,
      "description": "The phrase to measure, without quote marks."
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
  • run_peer_benchmark unknown never probed

    A fresh, citable comparison of one company's filed metric (revenue growth, gross margin, R&D or sales-and-marketing as a share of revenue) against 2-6 peers, latest fiscal year, from SEC EDGAR XBRL as filed. Identity, freshness, fiscal-year alignment and plausibility controls; every excluded peer is named with its reason; each figure cites its 10-K. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "ticker",
    "peers",
    "metric"
  ],
  "properties": {
    "peers": {
      "type": "string",
      "description": "2-6 peer tickers from the same list, comma-separated, e.g. \"CAG,CPB,KHC\"."
    },
    "metric": {
      "enum": [
        "revenue_growth",
        "gross_margin",
        "rd_intensity",
        "sm_intensity"
      ],
      "type": "string"
    },
    "ticker": {
      "enum": [
        "PEP",
        "KO",
        "K",
        "POST",
        "KDP",
        "CELH",
        "UTZ",
        "HRL",
        "GIS",
        "KHC",
        "CAG",
        "CPB",
        "HSY",
        "MDLZ",
        "SJM",
        "CLX",
        "CL",
        "CHD",
        "PG",
        "SMPL",
        "BRBR",
        "MSFT",
        "EA",
        "TTWO",
        "RBLX",
        "OMC",
        "STGW",
        "CRM",
        "HUBS",
        "TDOC",
        "TALK",
        "GDDY",
        "GEN",
        "NFLX",
        "AMZN"
      ],
      "type": "string",
      "description": "The company."
    }
  },
  "additionalProperties": false
}
    arguments 65 lines
  • run_ai_visibility unknown never probed

    Is a domain cited when ChatGPT, Claude, Gemini and Perplexity answer a buyer's question? The question is asked live of all four with web search on; the result is a measurement: per platform whether the domain was cited and at what position, how many platforms cite it, and the other domains cited most. It does not return the answers themselves. A platform that cites no sources is reported as not measured, and fewer than 3 measured platforms makes the run unsound. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "question",
    "domain"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "The domain to look for, e.g. example.com. Its subdomains count."
    },
    "question": {
      "type": "string",
      "maxLength": 100,
      "minLength": 10,
      "description": "The question a buyer would ask an AI assistant. No personal data."
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • get_decision_brief unknown 19m ago

    Everything public about one brief: the six decisions it covers with the evidence line for each, pages, edition, price, sample pages, free answers, guarantee, license and payment link. The PDF itself is delivered only after payment.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Brief id from list_decision_briefs, e.g. \"cpg-premium\"."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • search_cultmath unknown never probed

    Search the free CULT+MATH studies and answers (and the briefs) by keywords. Returns titles, URLs, dates, the lead finding and the brief that goes deeper.

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "kind": {
      "enum": [
        "any",
        "study",
        "answer",
        "brief"
      ],
      "type": "string",
      "description": "Restrict results. Default any."
    },
    "limit": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "Default 5."
    },
    "query": {
      "type": "string",
      "description": "Keywords, e.g. \"streaming ad tier\" or \"retailer concentration\"."
    }
  },
  "additionalProperties": false
}
    arguments 29 lines
  • get_decision_evidence unknown never probed

    Returns the full evidence for one decision once it is paid for. Pass the session_id from buy_decision_evidence, or the Checkout Session id of a full brief, team license, pack or all-access purchase that includes this decision.

    mcp-tool

    {
  "type": "object",
  "required": [
    "decision_id",
    "session_id"
  ],
  "properties": {
    "session_id": {
      "type": "string",
      "description": "A Stripe Checkout Session id (cs_live_...)."
    },
    "decision_id": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • buy_decision_evidence unknown never probed

    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. Returns a checkout URL for the user to approve and pay, and a session_id. After the user pays, call get_decision_evidence with both ids. Always show the price and get the user's go-ahead before sending them to pay.

    mcp-tool

    {
  "type": "object",
  "required": [
    "decision_id"
  ],
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "From list_decisions, e.g. \"cpg-premium/02\"."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_document unknown never probed

    Every published finding (question and answer) of one CULT+MATH study or answer page, with its date, license, citation line and related brief.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "A cultmath.com/research/... or /answers/... URL from search_cultmath, or its last path segment."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • run_filing_trend unknown never probed

    A fresh, citable measurement: what share of U.S. 10-K filers mention a phrase, year by year, from SEC EDGAR full-text search. Every run carries two controls ("competition" as the filer denominator; "shrinkflation", which must be 0) and its stated limits, plus a run id and a dated citation line. This tool only validates the request and returns a payment_url, the price and instructions; it charges nothing. Pay by POSTing to payment_url over MPP (HTTP 402, a Stripe shared payment token from your wallet). You are charged only if the run passes its controls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "phrase"
  ],
  "properties": {
    "end": {
      "type": "integer",
      "description": "Last year, not in the future. Default: this year. At most 10 years per run."
    },
    "start": {
      "type": "integer",
      "minimum": 2001,
      "description": "First year (2001 onward). Default: four years ago."
    },
    "phrase": {
      "type": "string",
      "maxLength": 80,
      "minLength": 3,
      "description": "The phrase to count, without quote marks, e.g. \"tariff\" or \"GLP-1\"."
    }
  },
  "additionalProperties": false
}
    arguments 24 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id e5712c82184c1261.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e5712c82184c1261/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/e5712c82184c1261/badge.svg)](https://brick.blue/agent/e5712c82184c1261?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.