ValueinValuein
MCP-first · works in Claude, Copilot, ChatGPT & Cursor

You bring the judgment. We bring the AI engine.

Codify your research process into agents that run in the AI you already use — point-in-time, survivorship-free, and reproducible on every company you cover.

You
requestresults
Your AI agentBYO key · zero-retention
Valuein

Valuein MCP Server

mcp.valuein.biz

point-in-time · survivorship-free

Datasets111M+ SEC facts
Tools95 MCP tools
SOPs28 agentic playbooks
Workflowschained, multi-step

one connector · one token · same intelligence in every AI

  • Point-in-time, no look-ahead
  • Every number auditable to its filing
  • Human-on-the-loop — you approve what matters
111M+
standardized_facts
income · balance · cash flow
19,000+
tickers
active + delisted, since 1993
<80ms
median_tool_latency
typed MCP calls
95
mcp_tools
+ 28 agentic workflows
0
model_temperature
deterministic managed runs
100%
facts_with_lineage
every number → a filing
Three ways to deploy

One token. Three channels.

One subscription, three ways in — an AI agent, a browser workspace, or your own code. Same data, same lineage, same persisted state underneath: save a thesis in Claude, see it in Cursor.

MCP Server

The agent you already use, now a cited equity analyst.

Agent-agnostic by design: Claude, Copilot, ChatGPT, Perplexity, Gemini, Grok, or Cursor — wired to 95 typed tools and 28 expert workflows. Works the moment you connect, pay per call to start, every result cited.

Connect your AI agent
mcp.valuein.biz/mcp
R
What's NVDA's FY2024 revenue and operating margin?
Claude Desktop·Sonnet 4.5

Calling Valuein MCP…

search_companiesNVDA → CIK 1045810
get_company_fundamentalsFY2024 · 10-K
get_financial_ratiosmargins · cash conversion
Workspace

Your agents run while you sleep. You approve what matters.

A browser research desk with your own LLM key — sealed for 24 hours, never trained on. Agent teams re-run your workflows on every new filing; every high-impact action waits for your approval. Human-on-the-loop, not human-out-of-the-loop.

Try the Workspace
valuein.biz/workspace
R
Equity research brief on NVDA, forensic depth.

Running flagship equity_research_brief SOP…

search_companiesresolve NVDA → CIK 1045810
get_company_fundamentalsrevenue · margins · cash flow
get_financial_ratiosROIC, FCF margin, leverage
forensic_auditaccruals · revenue quality flags
generate_research_brief_docxrendered → /r/nvda-2026-q1
Ask anything — wired to 95 SEC tools…
Python SDK

The backtest that can't cheat.

pip install, one token, 111M+ standardized facts through DuckDB — point-in-time, survivorship-free, zero look-ahead. The raw truth in your own code, not a black box.

Read the SDK docs
meta_research.py
running
from valuein_sdk import ValueinClient # Point-in-time SEC fundamentals — sample tier, no API keywith ValueinClient() as client: df = client.run_template( "fundamentals_by_ticker", ticker="META", ) print(df.head())
$python meta_research.py
Streaming 111M facts via DuckDB — point-in-time…
What we provide

Two datasets: financial fundamentals and smart-money.

Financial fundamentals

111M+ facts · 19,000+ companies · 1993–present

Free tier and up

Smart-money signals

78M+ rows · Forms 3/4/5/144 + 13F/13D/13G

Institutional

The method

The model never mints a number.

Typed tools return SEC-filed values; the model only arranges the words. Same inputs, same output — and every figure is one click from its filing.

Un-inventable

A tool returns the number.

META · op_income · FY2024

$69,380,000,000

fact_id 9f3c1b7e…as reported

There is no free-text digit to invent — the model selects a fact, it doesn't author one.

Reproducible

Same inputs, same output.

run · Mon 09:12 UTC$187.42
run · Fri 17:41 UTC$187.42
outputs identical

temperature 0 · point-in-time snapshots · deterministic tools. Research your firm can reproduce years later.

Auditable

One click to the filing.

verify_fact_lineage(fact_id)

sec.gov/ix?doc=…/meta-20241231.htm
Matches the 10-K

No re-running, no trust-me. An auditor clicks through and checks the figure against the original 10-K.

We didn't ask the model to stop hallucinating. We removed its ability to be the source of a digit.

Read the full methodology
The proof

Most “historical” data is a lie told in hindsight.

It silently overwrites with restatements and quietly drops the companies that failed. Both errors inflate every backtest. Here is what ours does instead — visibly.

query: get_company_fundamentals(as_of="2021-06-30")What a query dated 2021-06-30 returns — and what it is forbidden to see.
as_of · 2021-06-30
10-K FY2019
2020-02-26
10-Q Q1
2020-05-01
10-Q Q2
2020-07-30
10-K FY2020
2021-02-24
as originally reported
10-K/A FY2020
2021-11-09
restatement · filed later
10-Q Q3 2021
2021-12-03
visible at query datefiled later · walled offthe 10-K/A restatement is invisible to this query — no look-ahead
As reported vs restatedFY2020, $M. A point-in-time query never silently swaps one for the other.
Metricas reportedrestated
Revenue10,38810,388
Operating income2,1141,902
Net income1,6401,431
Diluted EPS3.052.66

verify_fact_lineage() → both versions retained · each keyed to its filing

The dead are still in the indexDelisted, bankrupt, merged, taken private — kept, not survivorship-pruned.
  • ENRNbankrupt · 2001
  • LEHbankrupt · 2008
  • WAMUseized · 2008
  • BBBYbankrupt · 2023
  • SIVBfailed · 2023
  • FTXcollapsed · 2022

get_pit_universe(date) → the index as it stood, not as it survived

The adoption gap

Adoption is solved. Trust is the bottleneck.

The blockers that keep agents stuck in pilot all reduce to one thing: an answer your firm can't stand behind. Valuein removes the cause, not the symptom.

Agents invent numbers

Typed tools only return SEC-filed values.

Nobody can defend the answer

fact_id + one-click lineage to the filing.

Autonomy nobody signed off on

Human-on-the-loop approval ledger.

Your data leaks to the vendor

BYO-LLM, zero-retention.

Pricing

Start on the house. Scale when the work does.

Begin on the S&P 500 with no card, then open the full universe and smart-money signals as the work grows. Paid plans are priced per seat — per person, never per firm.

Free — S&P 500

$0no card

Begin on the S&P 500, 1993–present.

  • Full S&P 500 history
  • MCP, SDK & Workspace
  • One token across channels
Start free

Pro

$49/mo per seat

The full universe for analysts & developers.

  • 19,000+ companies, incl. delisted
  • 15-year point-in-time window
  • 95 tools + 28 workflows + SDK
Go Pro

Institutional

$499/mo per seat

Full history, smart-money, redistribution.

  • 1993–present, all amendments
  • Insider + 13F smart-money data
  • Webhooks, SLA & redistribution
See Institutional

Add one connector. Get a research floor.

Free tier, no card — real filings in under 15 seconds. Connect an agent or open the Workspace to start.

Free S&P 500 tier — Pro from $49/moNo credit card requiredMCP · Workspace · Python SDK — one token