The thesis

Answer

A stock's full read in one call: the standing investment case, valuation off its filed financials, and the latest quarter.

TOOLanswer
Server
https://mcp.optimistfi.com/mcp
Authentication
None
Access
Read-only: it changes nothing
Example call
curl https://mcp.optimistfi.com/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"answer","arguments":{"entity":"NVDA"}}}'

When a model calls it

Models choose a tool from its description. This is the one the server publishes:

A stock's full read in one call: the standing investment case, valuation off its filed financials, and the latest quarter. Use when the user asks: is X a buy; is X cheap; what are X's earnings; how was X's quarter; did X beat. response_mode=plain for beginners. Not for: several companies → compare. Args: entity; response_mode.
  • is X a buy
  • is X cheap
  • what are X's earnings
  • how was X's quarter
  • did X beat

For something else: compare.

Parameters

entitystringrequired

The company: a ticker (AAPL, BRK.B), a company name (Apple) or an SEC CIK.

response_modestringdefault "standard"

standard
the full read with the investment case
plain
a short beginner-friendly explanation at the reading_level grade

Accepts standard, plain.

reading_levelinteger

With response_mode plain, who the explanation is written for: 5 a complete beginner, 10 a general reader, 13 an informed investor (unset reads as 13, with precise figures).

Accepts 5, 10, 13.

Response

A real response to the example call, trimmed: lists cut to two items, long text cut short. The result's content holds the answer as JSON text; parsed, it reads:

result.content · parsed
{
  "entity": {
    "ticker": "NVDA",
    "name": "NVIDIA CORP",
    "cik": "0001045810"
  },
  "type": "answer",
  "as_of": "2026-08-28T17:34:59Z",
  "confidence": "estimated",
  "source": {
    "name": "OptimistFi — valuation over filed financials + the investment thesis",
    "url": "https://optimistfi.com/stocks/NVDA",
    "license": "computed"
  },
  "data": {
    "valuation": [
      {
        "entity": {
          "ticker": "NVDA",
          "name": "NVIDIA CORP",
          "cik": "0001045810"
        },
        "type": "valuation",
        "direction": "backward",
        "as_of": "2026-10-12",
        "confidence": "confirmed",
        "source": {
          "name": "OptimistFi — ratios over the issuer's own filed financials",
          "url": "https://optimistfi.com/stocks/NVDA",
          "license": "computed"
        },
        "data": {
          "pe_ratio": 46.02,
          "price_to_sales": 25.59,
          "price_to_book": 24.13,
          "price_to_cash_flow": 53.79,
          "ev_to_ebitda": 41.56,
          "market_cap": 5525648000000,
          "enterprise_value": 5536571000000,
          "last_close": 229.28,
          "last_close_date": "2026-10-09",
          "fundamentals_period": "2026-01-25",
          "shares_outstanding_date": "2026-08-21"
        }
      }
    ],
    "thesis": {
      "thesis": "NVIDIA converts an outsized and growing wave of AI datacenter demand into very high-margin profits because its accelerator hardware + software ecosystem are the default choice for training and inference at scale.",
      "claims": [
        {
          "id": "ecosystem-lockin-drives-repeat-demand",
          "claim": "NVIDIA's developer-facing software and ecosystem create switching costs that convert AI demand into repeat buys of its accelerators, sustaining data-center revenue growth.",
          "why_it_matters": "If true, revenue growth will remain high and predictable as customers expand clusters around NVIDIA; if false, hyperscalers/custom silicon wins will cause demand to shift away and revenue growth will decelerate.",
          "rests_on": "revenue",
          "supporting_evidence": [
            "Revenue grew from $26.974B (FY2023) to $215.938B (FY2026), showing sustained, repeatable demand expansion tied to AI workloads.",
            "Item 1 Business describes NVIDIA as a pioneer in accelerated computing, implying a software+hardware ecosystem orientation that supports lock-in."
          ],
          "challenging_evidence": [
            "Hyperscalers develop and deploy custom accelerators at scale (e.g., in-house ASICs) and retool frameworks to favor those chips, reducing purchases of NVIDIA GPUs.",
            "Competitors (AMD, Intel, or cloud-vendor silicon) achieve software/driver parity and win benchmark-based migrations for training clusters."
          ],
          "metrics_and_events": [
            "Segmented data-center revenue (watch for any disclosed declines or market-share loss)",
            "Quarterly total revenue growth prints",
            "… 2 more"
          ],
          "status": "supported",
          "confidence": "medium",
          "sources": [
            "Item 1 Business",
            "https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=1045810&type=10-K"
          ],
          "grounded": true
        },
        {
          "id": "pricing-power-protects-gross-profit",
          "claim": "NVIDIA's architecture and scale give it pricing power that keeps gross margin very high, protecting earnings power even as volume grows.",
          "why_it_matters": "Sustained pricing power preserves high operating margins and cash conversion; loss of pricing power would compress margins and materially reduce intrinsic value.",
          "rests_on": "gross_profit",
          "supporting_evidence": [
            "Gross profit expanded from $15.356B (FY2023) to $153.463B (FY2026), implying consistently high gross dollars as revenue scaled.",
            "Operating income and net income grew faster than revenue, consistent with margin expansion and pricing power (operating_income: $3.297B → $130.387B, net_income: $4.368B → $120.067B)."
          ],
          "challenging_evidence": [
            "Competitors introduce lower-cost accelerators with comparable perf/W that force price competition (AMD MI-series, Intel/other datacenter silicon).",
            "Large customers secure long-term supply agreements or volume discounts that materially reduce ASPs."
          ],
          "metrics_and_events": [
            "Gross profit (annual and quarterly) and any disclosed gross margin percentage",
            "Announcements of competitor price cuts or subsidized cloud offerings",
            "… 1 more"
          ],
          "status": "supported",
          "confidence": "medium",
          "sources": [
            "Item 1 Business",
            "https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=1045810&type=10-K"
          ],
          "grounded": true
        },
        "… 3 more"
      ],
      "company_thesis": "NVIDIA's business captures AI-driven datacenter spend by selling purpose-built accelerators and a developer-facing software stack that create switching costs; product leadership, scale and ecosystem advantages let the company sustain premium pricing, convert sales into excepti…",
      "security_overlay": "The stock currently prices in continued exceptional revenue growth and unusually high operating margins. For the stock to outperform, NVIDIA must keep converting hyperscaler and enterprise AI budgets into GPU and software sales at current share levels (no material loss to cust…",
      "paragraph": "NVIDIA's story is that accelerated computing is the bottleneck for large-scale AI and NVIDIA supplies both the accelerators and the developer-facing software that make GPUs the practical default. The company has turned that position into rapidly rising revenue, massive gross p…",
      "central_debate": "Will NVIDIA sustain its product and ecosystem advantage (and therefore pricing and margins) as hyperscalers, cloud providers and competitors invest in alternative/custom accelerators?",
      "bull_case": "NVIDIA keeps its architectural and software lead, remains the default for AI training and inference, and thus sustains very high revenue growth and industry-leading margins. That combination drives exceptional free cash flow, which funds continuous innovation, capacity expansi…",
      "bear_case": "Hyperscalers and large cloud providers migrate major training workloads to custom accelerators or competitor silicon at scale, or open-source frameworks favor non‑NVIDIA stacks. That would take away NVIDIA's high-margin volume, force price competition, and materially compress …",
      "invalidation": "Widespread migration of hyperscaler/large-enterprise training deployments off NVIDIA GPUs to alternative/custom accelerators at scale (a driver-level loss of share and pricing power) that precedes declines in revenue and margins.",
      "catalysts": [
        "Quarterly revenue and operating margin prints (next several quarters) that reveal sustainment or erosion of margins",
        "New datacenter GPU / accelerator product launches and initial performance/price benchmarks",
        "… 2 more"
      ],
      "segments": [
        "Accelerated computing / datacenter AI (training & inference)",
        "Graphics & gaming GPUs (consumer)",
        "… 1 more"
      ],
      "open_questions": [
        "Detailed revenue mix by segment (data-center vs gaming vs software) and the percent of revenue from hyperscalers — not available in the provided fields.",
        "Explicit gross margin and operating margin percentages per segment and how much margin is tied to data-center vs other businesses.",
        "… 1 more"
      ],
      "last_evaluated": "2026-08-28"
    },
    "helps_and_hurts": {
      "breaks_the_case": "Widespread migration of hyperscaler/large-enterprise training deployments off NVIDIA GPUs to alternative/custom accelerators at scale (a driver-level loss of share and pricing power) that precedes declines in revenue and margins.",
      "by_claim": [
        {
          "claim": "NVIDIA's developer-facing software and ecosystem create switching costs that convert AI demand into repeat buys of its accelerators, sustaining data-center revenue growth.",
          "helps": [
            "Revenue grew from $26.974B (FY2023) to $215.938B (FY2026), showing sustained, repeatable demand expansion tied to AI workloads.",
            "Item 1 Business describes NVIDIA as a pioneer in accelerated computing, implying a software+hardware ecosystem orientation that supports lock-in."
          ],
          "hurts": [
            "Hyperscalers develop and deploy custom accelerators at scale (e.g., in-house ASICs) and retool frameworks to favor those chips, reducing purchases of NVIDIA GPUs.",
            "Competitors (AMD, Intel, or cloud-vendor silicon) achieve software/driver parity and win benchmark-based migrations for training clusters."
          ]
        },
        {
          "claim": "NVIDIA's architecture and scale give it pricing power that keeps gross margin very high, protecting earnings power even as volume grows.",
          "helps": [
            "Gross profit expanded from $15.356B (FY2023) to $153.463B (FY2026), implying consistently high gross dollars as revenue scaled.",
            "Operating income and net income grew faster than revenue, consistent with margin expansion and pricing power (operating_income: $3.297B → $130.387B, net_income: $4.368B → $120.067B)."
          ],
          "hurts": [
            "Competitors introduce lower-cost accelerators with comparable perf/W that force price competition (AMD MI-series, Intel/other datacenter silicon).",
            "Large customers secure long-term supply agreements or volume discounts that materially reduce ASPs."
          ]
        },
        "… 3 more"
      ],
      "bull_case": "NVIDIA keeps its architectural and software lead, remains the default for AI training and inference, and thus sustains very high revenue growth and industry-leading margins. That combination drives exceptional free cash flow, which funds continuous innovation, capacity expansi…",
      "bear_case": "Hyperscalers and large cloud providers migrate major training workloads to custom accelerators or competitor silicon at scale, or open-source frameworks favor non‑NVIDIA stacks. That would take away NVIDIA's high-margin volume, force price competition, and materially compress …"
    },
    "perps": {
      "base": "NVDA",
      "asOf": "2026-10-12T17:00:00Z",
      "venues": 26,
      "totals": {
        "openInterestUsd": 180869754,
        "openInterestChange24h": -0.06502,
        "fundingRateHourlyOiWeighted": 0.000004607,
        "fundingRateAnnualizedOiWeighted": 0.04036,
        "priceLow": 226.21,
        "priceHigh": 226.65
      },
      "units": {
        "rates": "fractions (0.0001 = 0.01%)",
        "funding": "what a long pays per hour (negative: shorts pay longs); fundingCumulative sums a venue's hourly rates over the window; predictedFunding is a venue's own estimate of a settlement still to come, where its reading publishes one",
        "money": "US dollars",
        "openInterestCap": "on Hyperliquid and its builder dexes: whether the market sits at its open-interest cap in the latest hourly reading (where it cannot grow its open interest), since when, and the cap in USD of one side's open interest where the dex publishes one"
      },
      "page": "https://optimistfi.com/perps/markets/nvda"
    }
  }
}

Fields are explained in Reading a response.

Errors

A call the server cannot run (a missing or invalid argument) comes back with isError: true and the reason in words. A company or market the server cannot match comes back as a result naming what was not found. See Errors and limits.
ScoutJUST THIS STORY

LET’S MAKE THIS USEFUL · 1 OF 5

How would you like me to explain this?

Tell me what you want from this read. Start with a quick note, then adjust the details. Your other stories stay as they are.

We’ll remember your view of this story. The published article stays unchanged.

THIS STORY’S READING VIEWStandard · The whole picture

Clear explanations with context. Both sides of the evidence.