Server definition

Hash: sha256:0aa97968f0c8ada0065fed28df9c9df14fea2cb3473a896090390f6d781f4e25
What it is: What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{
  "instructions": "Access S&P 500 market data from Quantustik: fear and greed, earnings calendars, SEC filings, insider and institutional activity. Quantustik publishes data only, no forecasts or recommendations. All outputs are for educational research only — not personalized financial advice. You do NOT need an API key — every tool is callable right now; anonymous requests share a per-IP hourly cap. Call get_started for quota details and list_capabilities to discover every tool and resource.",
  "tools": [
    {
      "description": "Get the earnings calendar (next + last report) for one S&P 500 ticker.\n\n    Earnings are a scheduled event. This tool surfaces the next-upcoming and\n    last-reported earnings dates and the days until the next one.\n\n    When no data is available (cold cache + no live source), `available` is\n    false and `next`/`last` are null; treat that as \"unknown\", not \"no earnings\".\n\n    Args:\n        ticker: Stock ticker symbol (e.g. \"AAPL\", \"MSFT\", \"NVDA\"). Case-insensitive.\n\n    Returns a dict with available, next, last, days_until_next, as_of and\n    disclaimer embedded in the payload.\n    ",
      "inputSchema": {
        "properties": {
          "ticker": {
            "title": "Ticker",
            "type": "string"
          }
        },
        "required": [
          "ticker"
        ],
        "title": "get_earnings_calendarArguments",
        "type": "object"
      },
      "name": "get_earnings_calendar",
      "outputSchema": null
    },
    {
      "description": "Get the latest Fear and Greed index value.\n\n    Sourced from the CNN Fear and Greed model, cached and refreshed periodically.\n    Values range 0 (Extreme Fear) to 100 (Extreme Greed).\n\n    Returns a dict with value (0-100), label (e.g. \"fear\"), and timestamp, plus\n    `current` ({score, rating, updated_at}), `history`, and the per-component\n    `sub_indicator_scores`.\n    ",
      "inputSchema": {
        "properties": {},
        "title": "get_fear_greedArguments",
        "type": "object"
      },
      "name": "get_fear_greed",
      "outputSchema": null
    },
    {
      "description": "Get the \"Lazy Prices\" 10-K/10-Q language diff for one ticker.\n\n    Compares the two most recent 10-K (year-over-year, default) or 10-Q\n    (quarter-over-quarter) filings' Risk Factors (Item 1A) and MD&A\n    (Item 7 for 10-K, Item 2 for 10-Q) sections, pre-chewed so you don't have\n    to parse raw filing HTML yourself: a real TF-IDF cosine similarity score\n    between the two extracted section texts, plus the top added/removed\n    sentences from a real sentence-level diff, plus a one-line AI summary\n    grounded strictly in those diffed sentences (`summary_source: \"llm\"`), or\n    a factual sentence built purely from the computed similarity/counts when\n    no LLM is available (`summary_source: \"computed\"`) — never fabricated\n    either way. Every result links to BOTH source filings via\n    `filings[].accession_url` — verify anything before acting.\n\n    Cites a known academic finding: Cohen, Malloy & Nguyen (2020), \"Lazy\n    Prices\", Journal of Finance — YoY changes in 10-K Risk Factors/MD&A\n    language are historically return-predictive. This is a third-party\n    academic result cited for context, NOT a claim or backtest result of\n    this app.\n\n    An empty `sections` dict is a valid, honest answer when the ticker has\n    fewer than 2 filings of the requested form on file, or a section\n    couldn't be reliably extracted from both filings (known gap: this\n    extractor targets the common modern EDGAR HTML filing format used by\n    large-cap names; older/non-standard filing formats may not extract).\n\n    Read-only surfacing: this is information, not a recommendation.\n\n    Args:\n        ticker: Stock ticker (e.g. \"AAPL\"). Case-insensitive.\n        form: \"10-K\" (year-over-year, default) or \"10-Q\" (quarter-over-quarter).\n\n    Returns: ticker, form, filings (the two compared filings with\n    accession_url), sections (keyed by \"risk_factors\"/\"mda\", each with\n    similarity, added_sentences, removed_sentences, summary,\n    summary_source), generated_at, disclaimer.\n    ",
      "inputSchema": {
        "properties": {
          "form": {
            "default": "10-K",
            "title": "Form",
            "type": "string"
          },
          "ticker": {
            "title": "Ticker",
            "type": "string"
          }
        },
        "required": [
          "ticker"
        ],
        "title": "get_filing_language_diffArguments",
        "type": "object"
      },
      "name": "get_filing_language_diff",
      "outputSchema": null
    },
    {
      "description": "Get SEC 8-K event digest — per-ticker detail or a site-wide recent feed.\n\n    New EDGAR ingestion (unlike get_insider_pulse's Form 4 data, which was\n    already ingested): polls 8-K filings and pre-chews each one so you don't\n    have to parse raw filing HTML yourself. Event type comes from the\n    filing's OWN structured SEC Item number(s) — GROUND TRUTH, never\n    LLM-guessed (e.g. Item 5.02 = exec departure/appointment, Item 2.02 =\n    earnings results, Item 2.01 = M&A completion, Item 4.02 = restatement).\n    The `summary` field is a one-line AI narration grounded in the actual\n    filed document text (`summary_source: \"llm\"`), or a factual sentence\n    built purely from the Item label(s) when no document excerpt was\n    available (`summary_source: \"item_labels\"`) — never fabricated content\n    either way. Every filing links to its source SEC filing via\n    `accession_url` — verify anything before acting.\n\n    Two modes:\n      - ticker set: per-ticker view — up to 15 most-recent 8-Ks over the\n        trailing ~6 months.\n      - ticker omitted: site-wide feed — up to 30 most-recent 8-Ks across\n        the S&P 500 (top-100) universe in the trailing ~2 weeks. An empty\n        `filings` list is a valid, honest answer on a quiet news day.\n\n    Read-only surfacing: this is information, not a recommendation.\n\n    Args:\n        ticker: Optional. Stock ticker for the per-ticker view (e.g. \"AAPL\").\n                Omit for the site-wide recent feed. Case-insensitive.\n\n    Returns per-ticker: ticker, filings, generated_at, disclaimer.\n    Feed: tickers_scanned, filings, generated_at, disclaimer.\n    ",
      "inputSchema": {
        "properties": {
          "ticker": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Ticker"
          }
        },
        "title": "get_filings_digestArguments",
        "type": "object"
      },
      "name": "get_filings_digest",
      "outputSchema": null
    },
    {
      "description": "Get SEC Form 4 insider-trading activity — per-ticker detail or S&P 500 screener.\n\n    Surfaces already-ingested Form 4 filings (the same Form 4 feed behind the\n    market model's `form4` stage) pre-chewed into analytical context so you\n    don't have to parse raw XBRL yourself: buyer role (officer / director /\n    10% owner), transaction size vs that SAME insider's own historical buy\n    pattern (`size_vs_own_median`, `is_unusually_large` when >=2x their own\n    median), and cluster-buy detection (`is_cluster` — 3+ distinct insiders\n    buying the same ticker within a 10-day window, historically the stronger\n    signal vs a single insider's trade). Every transaction links to its\n    source SEC filing via `accession_url` — verify anything before acting.\n\n    Two modes:\n      - ticker set: per-ticker view — up to 40 most-recent Form 4 transactions\n        over the trailing year plus `cluster_buy_active`.\n      - ticker omitted: S&P 500 (top-100) screener — tickers with a cluster\n        buy or an unusually-large buy in the last 30 days. An empty\n        `results` list is a valid, honest answer; most weeks most tickers\n        show nothing notable.\n\n    Read-only surfacing: this is information, not a recommendation.\n\n    Args:\n        ticker: Optional. Stock ticker for the per-ticker view (e.g. \"AAPL\").\n                Omit for the S&P 500 screener. Case-insensitive.\n\n    Returns per-ticker: ticker, transactions, cluster_buy_active, generated_at,\n    disclaimer. Screener: tickers_scanned, results, generated_at, disclaimer.\n    ",
      "inputSchema": {
        "properties": {
          "ticker": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Ticker"
          }
        },
        "title": "get_insider_pulseArguments",
        "type": "object"
      },
      "name": "get_insider_pulse",
      "outputSchema": null
    },
    {
      "description": "Get 13F whale summaries + SC 13D/G activist alerts for one ticker.\n\n    Final slice of the SEC EDGAR AI-digest layer. Two surfaces\n    in one payload:\n\n    `whale_summary` — QoQ (quarter-over-quarter) change in institutional\n    ownership across a curated ~50-filer 13F universe (activist funds,\n    quant shops, mega index managers, tiger cubs, sovereign wealth, etc.):\n    new positions opened, positions closed, and the largest\n    increases/decreases by dollar value between the two most recent 13F\n    quarters on file. Pure computed deltas — no LLM narration, just real\n    numbers. Institutional filer names come from SEC's own submissions data\n    (ground truth), and every filer row links to its source 13F accession\n    via `accession_url`. When there's genuinely nothing to compute (ticker\n    not held by any tracked filer, or fewer than 2 quarters on file), the\n    `narration` field says so plainly instead of a fabricated result.\n    A filer only ever appears in `closed_positions` when there is an actual\n    filing from that filer covering the latest quarter that omits this\n    ticker's cusip; a filer simply absent from the latest snapshot with no\n    filing on file for that quarter at all lands in `no_recent_filing`\n    instead — never treated as a sale. Absence of a filing is not evidence\n    of a sale.\n\n    `activist_alerts` — recent Schedule 13D (activist/control intent) and\n    13G (passive >5% stake) filings. 13D entries carry a one-line AI summary\n    grounded STRICTLY in the filing's own Item 4 (\"Purpose of Transaction\")\n    text when it can be confidently extracted (`summary_source: \"llm\"`) —\n    never an invented intent; otherwise a factual fallback sentence\n    (`summary_source: \"item_label\"`). 13G entries get a structured, non-AI\n    note (`summary_source: \"structured\"`) since 13G is reserved for passive\n    filers with nothing to narrate beyond the threshold crossing. Every\n    alert links to its source filing via `accession_url`.\n\n    Read-only surfacing: this is information, not a recommendation.\n\n    Args:\n        ticker: Stock ticker (e.g. \"AAPL\"). Case-insensitive.\n\n    Returns: ticker, whale_summary (cusip, quarters, new_positions,\n    closed_positions, no_recent_filing, increased, decreased, narration),\n    activist_alerts (list of filings with form, reporting_person, summary,\n    summary_source, accession_url), generated_at, disclaimer.\n    ",
      "inputSchema": {
        "properties": {
          "ticker": {
            "title": "Ticker",
            "type": "string"
          }
        },
        "required": [
          "ticker"
        ],
        "title": "get_institutional_activityArguments",
        "type": "object"
      },
      "name": "get_institutional_activity",
      "outputSchema": null
    },
    {
      "description": "Onboard to the Quantustik API/MCP: anonymous access and quotas.\n\n    No API key is needed — every tool is callable right now under an\n    anonymous per-IP hourly cap. Returns the live keyless/free-key request\n    quotas (pulled live from server config) plus the optional key-issuance\n    URL and auth header format. Pure informational — no auth required to\n    call it.\n    ",
      "inputSchema": {
        "properties": {},
        "title": "get_startedArguments",
        "type": "object"
      },
      "name": "get_started",
      "outputSchema": null
    },
    {
      "description": "List all available Quantustik MCP tools and resources.\n\n    Use this as the entry point when a user asks what can you do with\n    Quantustik, or to discover the full surface area of the server.\n\n    Returns a structured description of every tool and resource.\n    ",
      "inputSchema": {
        "properties": {},
        "title": "list_capabilitiesArguments",
        "type": "object"
      },
      "name": "list_capabilities",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:0aa97968f0c8ada0065fed28df9c9df14fea2cb3473a896090390f6d781f4e25 | sha256sum