Revelata deepKPI

Fundamental data, including operating KPIs, you can't even find on Bloomberg — pre-structured, fully cited, and agent-ready.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • 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
  • 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
  • Query Company Id: Look up a company's identifier by name. For US companies, this is the SEC CIK value.

What data it sees

Do you need an account

No: the server works without sign-in

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, or find us on GitHub.

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.

How to connect

How to connect Revelata deepKPI to Claude

The server address to paste into Claude settings:

https://deepkpi-mcp--revelata.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Revelata deepKPI to ChatGPT

The server address to paste into ChatGPT settings:

https://deepkpi-mcp--revelata.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Revelata deepKPI to Cursor

The server address to paste into Cursor settings:

https://deepkpi-mcp--revelata.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

search_kpisSearch 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_kpisList 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_idLook up a company's identifier by name. For US companies, this is the SEC CIK value.
get_company_summaryFetch 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_segmentsFetch 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_searchFind 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_markdownsList 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_markdownFetch 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_markdownsDEPRECATED alias. Use `list_sec_filing_markdowns`.
get_sec_markdownDEPRECATED alias. Use `get_sec_filing_markdown`.