Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the SEC Fundamentals API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmultyplylabs.com%2Fmultyplylabs" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmultyplylabs.com%2Fmultyplylabs" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with SEC Fundamentals API.
Resolve a ticker, CIK, or company name to the SEC CIK for free
Read clean annual income statement, balance sheet, cash flow, and ratios for a company by fiscal year
Pull reported XBRL facts mapped to 61 canonical concepts with units, periods, and filing provenance
List a company's 10-K, 10-Q, 8-K, Form 4, and other filings with direct document URLs
GET STARTED
Summarise Form 4 insider buying and selling, 13F institutional holder changes, and FINRA short-volume ratio
Screen US public companies by metric filters such as gross_margin above 0.6 for a fiscal year
Benchmark a metric against industry percentiles by SIC group and revenue size, or compare one company to its peers
Patterns agents use SEC Fundamentals API for, with concrete tasks.
★ AI research agent answering fundamentals questions
An AI agent asked 'how have Apple's margins changed over five years' needs filed numbers, not a guess. Through Jentic the agent searches for 'get annual financial statements for a company', first calls the free company lookup to turn AAPL into a CIK, then loads the financials operation with its input schema and requests the fiscal-year range, with the API key injected at call time. It answers from statement rows and derived ratios such as gross margin and operating margin.
Call GET /company/lookup with q=AAPL, then GET /company/{cik}/financials with fy_from=2021 and fy_to=2025 and report gross margin per year
Fundamentals stock screen
An investor building a watchlist starts from criteria rather than names. The screen route takes a fiscal year and a JSON list of metric, operator, and value filters, such as gross_margin above 0.6 and revenue above 1e9, and returns matching companies with names, tickers, industries, and the metric values. This is research data, not investment advice.
Call GET /screen with fy=2024 and filters [["gross_margin",">",0.6],["revenue",">",1e9]] and return the top 20 tickers
Peer benchmarking for a valuation memo
An analyst needs to know whether a company's debt-to-equity or margins are unusual for its sector. The compare route places one company's metrics beside its industry cohort's percentiles for a fiscal year, and the aggregate route returns p10 to p90, mean, and company count for any metric by 2-digit SIC group and size bucket from micro to mega.
Call GET /compare/{cik} with fy=2024 for the company, then GET /aggregate/{metric} for gross_margin with industry=73 and size=large
Insider and institutional positioning check
Before digging into a stock, a researcher checks who is buying. The insider route summarises recent Form 4 open-market buys versus sales with officer and director roles and 10b5-1 flags, the institutional route returns the 13F holder count and quarter-over-quarter change, and the short route gives the FINRA daily short-volume ratio over roughly 20 trading days.
Call GET /company/{cik}/insider with months=6, GET /company/{cik}/institutional, and GET /company/{cik}/short for one CIK and summarise the positioning
16 endpoints — the sec fundamentals api serves normalized sec edgar xbrl financial data for us public companies, keyed by cik.
METHOD
PATH
DESCRIPTION
/company/lookup
Find a company's CIK
/company/{cik}/financials
Get annual statements and ratios
/company/{cik}/facts
Get normalized XBRL facts
/company/{cik}/filings
List SEC filings
/company/{cik}/insider
Get Form 4 insider transactions
/screen
Screen companies by metrics
/compare/{cik}
Compare a company with its peers
/aggregate/{metric}
Get industry benchmark percentiles
/company/lookup
Find a company's CIK
/company/{cik}/financials
Get annual statements and ratios
/company/{cik}/facts
Get normalized XBRL facts
/company/{cik}/filings
List SEC filings
/company/{cik}/insider
Get Form 4 insider transactions
/screen
Screen companies by metrics
/compare/{cik}
Compare a company with its peers
/aggregate/{metric}
Get industry benchmark percentiles
What agents get from Jentic-routed access to this vendor.
Setup
Wiring SEC Fundamentals by hand means resolving tickers to CIKs, sending an X-API-Key on paid routes, and handling a 402 x402 payment challenge if the key is missing. Through Jentic you install once, import SEC Fundamentals from the API Directory, store the key once, and your agent calls it.
Permission scoping
SEC Fundamentals puts the company's CIK in the URL path, as in /company/{cik}/financials, so a rule can pin your agent to one company and the operations you pick. You choose the operations it may call, so market-wide routes like the screener and curated insights are not included unless you add them.
Credential isolation
Your SEC Fundamentals API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'get annual financial statements for a company' or 'screen stocks by gross margin', and Jentic returns the matching SEC Fundamentals operation with its input schema, including the cik, fy, and filters parameters, so the agent calls it correctly.
Alternatives and complements available in the Jentic catalogue.
Specific to using SEC Fundamentals API through Jentic.
What authentication does the SEC Fundamentals API use?
Per its OpenAPI spec, the paid routes declare an API key sent in the X-API-Key header, and a request with a valid key is served without payment. Without a key, a paid route answers 402 with an x402 USDC payment challenge. The health, catalog, company lookup, spotlight, and insights list routes are free and need neither. Through Jentic your key is held by your own instance and injected at call time.
How do I find a company's CIK with the SEC Fundamentals API?
Call GET /company/lookup with q set to a ticker such as AAPL or BRK.B, CIK digits, or part of a company name. It is free, returns up to 25 matches with cik, name, tickers, and SIC description, and the CIK it returns is what every /company/{cik} route takes.
What are the rate limits for the SEC Fundamentals API?
The OpenAPI spec does not specify rate limits. Contact help@multyplylabs.com, the support address named in the spec, or see https://sec.multyplylabs.com for current limits and API key terms.
How do I pull a company's annual financials through Jentic?
Search Jentic for 'get annual financial statements for a company', load GET /company/lookup to resolve the ticker, then load GET /company/{cik}/financials and execute it with the CIK and an optional fy_from and fy_to range. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the SEC Fundamentals API?
Yes. Write a rule that allows only GET /company/lookup and the financials route for one CIK, such as /company/320193/financials, and the agent can research that company's statements but cannot run screens or market-wide insights on your key. Every call is logged so you can see what it queried.
Is the SEC Fundamentals API investment advice?
No. The spec labels the signal, insider, institutional, short, and insight routes as research data, not investment advice, and states that Multyply Labs is not affiliated with the U.S. Securities and Exchange Commission.
For Agents
Look up a US public company's CIK, then read its normalized SEC financials, filings, insider trades, institutional ownership, and peer benchmarks, or screen companies by metrics.
Use for: Find the CIK for Apple, Get Microsoft's annual revenue and gross margin since 2018, List the latest 10-K and 10-Q filings for a company, Check whether insiders have been buying NVIDIA stock this year
Not supported: Does not provide stock prices, place trades, or cover non-US or private companies. Use for normalized SEC filing data and fundamentals research on US public companies only.
The SEC Fundamentals API serves normalized SEC EDGAR XBRL financial data for US public companies, keyed by CIK. It resolves a ticker or company name to a CIK for free, then returns reported facts mapped to 61 canonical concepts, clean annual statements with derived ratios such as gross margin, ROE, and debt-to-equity, and the filing index with direct document URLs. Further routes cover Form 4 insider transactions, 13F institutional ownership, FINRA short-volume ratios, a composite factor scorecard, industry benchmark percentiles, peer comparison, a fundamentals stock screener, and curated market-wide insights. Paid routes accept an API key or an x402 USDC payment, and the service is not affiliated with the U.S. Securities and Exchange Commission.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>