The unified database of public-company filings.
Every annual, quarterly, interim, and ad-hoc report from listed companies — searchable, structured, free for the web. An API and an MCP server for everything else.
Free, for everyone.
Search, browse, and read every filing in the index. No account, no paywall, no tracker. The web product is the public utility.
- —Full-text search across 21.5 million filings
- —Per-company pages with KPIs and history
- —Markdown export — one click
- —MCP server, free for any LLM client
Paid, for builders.
A typed REST API over the same index. Same filings, structured for production — bulk pulls, webhooks, redistribution rights.
- —Markdown, JSON, and original PDF
- —Webhooks on new filings · < 60 s
- —SLAs from p99 99.9 % upward
- —Bulk + redistribution licensing
Use it inside your LLM client.
A free, open-source MCP server. 60-second setup in any compliant client. Three popular ones below.
Claude Desktop
Add a single block to claude_desktop_config.json. Filings become callable in any conversation.
Claude Code
One claude mcp add command. The agent has the index in-tool while you build.
ChatGPT
Custom GPT or Connectors. Surface every filing inside ChatGPT for research, analysis, and drafting.
Setup guide →
"FinancialReports provided the critical data foundation for my thesis. Accessing a clean, historical dataset of European…"
"Comparing informational content across European borders is notoriously difficult due to format fragmentation. Financial…"
"The difference between a good paper and a top-tier publication is often the granularity of the data. FinancialReports g…"
"Our analysis requires a global view of innovation. When we needed to expand beyond Europe into complex Asian markets, F…"
"The speed and granularity were exactly what we needed. FinancialReports didn't just give us a list; they helped us fix …"
"Before this partnership, 80% of a PhD candidate's time was spent scraping and cleaning PDFs. Now, we stream clean, stru…"
What the index does.
The work between a regulator's PDF and a usable record — done once, exposed cleanly.
Indexed in < 60 s.
New filings land in the index seconds after publication. Webhooks fire under 90 seconds for paid clients.
2026-05-02 · 14:22 UTC + Adidas AG · Q1 2026 · 88 pp
PDFs become Markdown.
Every filing is normalised to clean Markdown — tables intact, footnotes attached. ~70 % token reduction vs. PDF text.
# Adidas AG — Annual 2024 ## Consolidated income statement | Item | 2024 | 2023 |
Tickers, ISINs, LEIs.
Every entity is resolved across regulators, exchanges, and identifier systems. Query by any. Get the same record.
ADS · DE000A1EWWW0 LEI · 529900D6BF99LW9R2E68 → Adidas AG (Germany)
Built for the way LLMs actually read.
A 412-page PDF is not a context window. Markdown is shorter, cleaner, and keeps the structure that footnotes and tables depend on.
Who builds on it.
Quant research, AI builders, newsrooms. Different shapes, same data layer.
Free for the web.
Paid for the API.
Search the index without signing up. When you're ready to ship, get an API key and start pulling Markdown in production.




