Datavidence Financials

What you get

Every value is also source-linked back to its SEC filing — accession, filed date, a direct EDGAR URL, and the us-gaap tag it was read from (tag order per field) — when you set include_provenance.

Use it in your AI agent (MCP)

Datavidence Financials is also a Model Context Protocol server, so LLM agents (Claude Desktop and any MCP-compatible client) can call it as tools. It’s published on the official MCP registry as ai.datavidence/datavidence-financials.

Run it — no signup

FL_API_KEY=sandbox_demo_key uvx datavidence-financials

The sandbox_demo_key returns sample data with no account — swap in your key for live data.

Claude Desktop

{
  "mcpServers": {
    "datavidence-financials": {
      "command": "uvx",
      "args": ["datavidence-financials"],
      "env": { "FL_API_KEY": "sandbox_demo_key" }
    }
  }
}

Restart Claude Desktop, then ask: “Get AAPL’s FY2023 financials with ratios.”

Tools

get_financials normalized three statements for a company & fiscal year (supports as_of, provenance, ratios).
get_financials_batch up to 25 companies in one call.
list_filings discover a company’s recent SEC filings.
get_revisions how a year’s figures changed across filings — as reported, then restated.
search_companies find a ticker & CIK by company name.
get_usage your quota — free, consumes nothing.
Source & docs: GitHub · PyPI.

Plans & API keys

Every plan gets the same data and the full API — plans differ in monthly volume, and Pro and Business also include the point-in-time bulk file. The Free plan includes 1,500 requests a month, and paid plans start at $29 a month. Keys are issued through RapidAPI. See pricing →

Base URL & authentication

Authenticate with an X-API-Key header on every request. Errors use a standard { "status": "error", "error": { "code", "message" } } envelope, and every response carries X-RateLimit-Limit / Remaining / Reset.

Quickstart

cURL

curl -H "X-API-Key: sandbox_demo_key" \
  "https://api.financials.datavidence.ai/v1/extract-ledger?ticker=AAPL&year=2023&include_ratios=true"

Python

import requests

BASE = "https://api.financials.datavidence.ai"
headers = {"X-API-Key": "sandbox_demo_key"}  # swap for your key

r = requests.get(
    f"{BASE}/v1/extract-ledger",
    params={"ticker": "AAPL", "year": 2023, "include_ratios": True},
    headers=headers, timeout=30,
)
r.raise_for_status()
data = r.json()["data"]
print(data["income_statement"]["total_revenue"], data["ratios"]["net_margin"])

Node.js (18+)

const BASE = "https://api.financials.datavidence.ai";
const url = new URL(BASE + "/v1/extract-ledger");
url.search = new URLSearchParams({ ticker: "AAPL", year: "2023", include_provenance: "true" });

const res = await fetch(url, { headers: { "X-API-Key": "sandbox_demo_key" } });
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const { data } = await res.json();
console.log(data.income_statement.total_revenue, data.provenance.income_statement.total_revenue.source_url);

Go

req, _ := http.NewRequest("GET",
    "https://api.financials.datavidence.ai/v1/extract-ledger?ticker=AAPL&year=2023", nil)
req.Header.Set("X-API-Key", "sandbox_demo_key")
resp, err := http.DefaultClient.Do(req)
// ... check err, resp.StatusCode, then json.Decode(resp.Body)

Endpoints

GET /v1/extract-ledger normalized three-statement financials for a fiscal year.
GET /v1/extract-ledger/batch the same for up to 25 companies in one request.
GET /v1/revisions how a fiscal year’s figures changed across filings.
GET /v1/companies find a company’s ticker and CIK by name.
GET /v1/submissions trimmed SEC submissions index (recent filings).
GET /v1/usage your current quota — free, doesn't consume a request.
Full schemas in the API reference.

Disclaimer