目录 / Revelata deepKPI
Revelata deepKPI
Fundamental data, including operating KPIs, you can't even find on Bloomberg — pre-structured, fully cited, and agent-ready. # Deep fundamental data for financial AI, delivered over MCP Most finance APIs give you stock prices and standard three-statement data. But the fundamental data that actually drives analysis — comparable sales, ARPU, unit counts, backlog, segment-level revenue, management guidance, non-GAAP breakouts — lives in the text, tables, and charts of SEC filings, and it never makes it into those feeds. Revelata's deepKPI surfaces and pre-structures exactly that information into KPI time series, with sentence-level citations for every data point, so you and your agent can trust the numbers. We pair this with the underlying textual context and commentary, so your AI agents become analysts you can finally trust. ## What you get: - **3.3M company-specific KPI time series** across US public companies (S&P 500, 400, 600), structured as queryable time series with 10+ years of history and daily updates - **Natural-language KPI discovery and semantic search** — ask "Olive Garden foot traffic" or "AI capex guidance" and find the right metric without knowing the filing's exact wording - **SEC filings (10-K, 10-Q, 8-K) converted to markdown** with tables, charts, and structure preserved — retrievable in full so your agent can quote management verbatim - **Thematic company discovery** — semantic search across 10-K-derived summaries to surface companies by what they actually do, not just by SIC code - **Company summaries and segment breakdowns** on demand, derived from each company's latest 10-K ## Built for agents that need to be right. We provide trusted context for your financial AI agents. Every returned KPI data point carries its unit, scale, period, and a link to the exact source sentence. Every filing retrieval returns verbatim markdown, so agents don't paraphrase material facts. ## Agent skills also available Companion skills that teach agents how to use these tools for common workflows — seasonality analysis, implied metric derivation, analyst report pressure-testing, benchmarking, and more — are published separately in the Smithery Skills directory under [revelata](https://smithery.ai/skills/revelata/equity-research-and-analysis), or find us on [GitHub](https://github.com/revelata/deepkpi-agents). ## Free to try. 100 free credits/month per user. Lookups and filing listings are always free; extraction and search calls are priced per result. International coverage (Japan, China, Hong Kong, and Singapore) available to enterprise clients.
接入信息
- 传输形态
- http
- 鉴权方式
- 鉴权未知
- 端点
https://deepkpi-mcp--revelata.run.tools
{
"mcpServers": {
"Revelata deepKPI": {
"url": "https://deepkpi-mcp--revelata.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| search_kpis | Search for KPIs of a company by semantic similarity. Each result costs 1 credit (max 15). Default is 3 — start small and increase only if needed. Best practice: call list_kpis first (free) to discover exact KPI names, then use those names as targeted queries here instead of requesting many results. Omit source to search across all filing types; set to '10-K', '10-Q', or '8-K' to restrict. For US companies, company_id is the SEC CIK; if you only have a company name, look up company_id with the query_company_id tool first. |
| list_kpis | List all available KPIs for a company, organized by category. This is free and the recommended first step before calling search_kpis — use the returned KPI names to craft precise, low-cost searches. Omit source to list all; set to '10-K', '10-Q', or '8-K' to filter. For US companies, company_id is the SEC CIK; if you only have a company name, look up company_id with the query_company_id tool first. |
| query_company_id | Look up a company's identifier by name. For US companies, this is the SEC CIK value. |
| get_company_summary | Fetch a narrative company summary derived from the company's latest 10-K. Costs 3 credits per successful call. For US companies, company_id is the SEC CIK; if you only have a company name, look up company_id with the query_company_id tool first. |
| get_company_segments | Fetch a structured breakdown of business segments derived from the company's latest 10-K. Costs 3 credits per successful call. For US companies, company_id is the SEC CIK; if you only have a company name, look up company_id with the query_company_id tool first. |
| company_summary_search | Find companies by semantic similarity to their 10-K-derived company summary. Costs 1 credit per company returned (max 15 via top_k_companies); empty results cost nothing. Use when the user wants peers, thematic screens, or companies matching a business description before drilling into KPIs. |
| list_sec_filing_markdowns | List SEC filings available as markdown for a given CIK. Free (no credits). Use this to discover valid `acc_no` and `seq_no` values before fetching content. `form_type` can be omitted to include all forms under the CIK. |
| get_sec_filing_markdown | Fetch the markdown content for a specific SEC filing (`acc_no`) and sequence (`seq_no`, default 1). Costs 10 credits per successful call. When the user asks “what did they say” / “what comments were made” / “exact language”, quote verbatim snippets from the returned markdown rather than paraphrasing. |
| list_sec_markdowns | DEPRECATED alias. Use `list_sec_filing_markdowns`. |
| get_sec_markdown | DEPRECATED alias. Use `get_sec_filing_markdown`. |
提交举报 / 纠错
侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。