Skip to main content
Glama
datavidence-financials

datavidence-financials

Official

Datavidence Financials — MCP Server

Normalized US-GAAP financial statements for every SEC XBRL filer — point-in-time, as originally reported — as MCP tools for your AI agent (or a plain REST API).

PyPI Python versions License: MIT MCP registry M8ven Score

Language models are good at reasoning about financial statements and bad at getting them. SEC EDGAR has the data, but its XBRL is a thicket of inconsistent tags, renamed concepts, and per-filer quirks — so agents either hallucinate the numbers or you spend weeks building a normalization layer. This is that layer: your agent asks for a company's financials and gets a clean, consistent answer — over the Model Context Protocol, or as a plain REST API.

⭐ If this is useful, please star the repo. It's a solo, early project, and stars are how other developers find it.

Claude calls the Datavidence Financials get_revisions tool: Pfizer's FY2019 revenue as filed ($51.75B) and as it reads today ($40.9B), with links to the SEC filings

This is the open-source, AI-native layer for the Datavidence Financials API — a standalone stdio server that forwards over HTTPS to the REST API (bring your own key). The connector is MIT-licensed; the underlying API is a commercial service.

Try it in 30 seconds (no signup)

Run it with no clone using uv — it installs into a throwaway environment:

FL_API_KEY=sandbox_demo_key uvx datavidence-financials

sandbox_demo_key returns sample data with no signup — good for a first run. Set FL_API_KEY to your real key for live SEC data. The server speaks MCP over stdio, so an MCP client (e.g. Claude Desktop, below) launches it.

Or install it as a persistent tool with pipx:

pipx install datavidence-financials
FL_API_KEY=sandbox_demo_key datavidence-financials

Related MCP server: filingrail-mcp

Connect by URL (no install)

Clients that support remote MCP servers (streamable HTTP) can connect without installing anything:

URL

Key

Data

https://mcp.financials.datavidence.ai/mcp

none

sample (AAPL FY2023)

https://mcp.financials.datavidence.ai/rapidapi/mcp

your RapidAPI key, as X-API-Key or Authorization: Bearer

live SEC data, metered by RapidAPI against your plan

Claude Code:

claude mcp add --transport http datavidence-financials \
  https://mcp.financials.datavidence.ai/rapidapi/mcp \
  --header "X-API-Key: YOUR_RAPIDAPI_KEY"

For the sample data, use the /mcp URL and leave out the header.

claude.ai: add https://mcp.financials.datavidence.ai/mcp as a custom connector with no sign-in. claude.ai can't send an API key for most accounts yet, so it gets the sample data for now.

Why it's different

  • Point-in-time, as originally reported. Pass an as_of date and you get the figures as they stood then — no look-ahead bias from later restatements. The thing backtests quietly get burned without.

  • Normalized to one schema. EDGAR's XBRL tags drift between filers and change over the years. We map them to a single US-GAAP income statement, balance sheet, and cash flow — including the awkward cases (noncontrolling interest, mezzanine/temporary equity, non-calendar fiscal years) — so you never parse a filing.

  • Every SEC XBRL filer. Coverage is the whole SEC XBRL universe (~2009 to present), fetched and normalized on demand — any CIK with XBRL facts, not a curated subset.

  • Source-linked, too. Turn on provenance and every value carries its SEC accession, filed date, and a direct EDGAR URL — so the model cites the filing instead of inventing a number.

Honest scope: US-GAAP only (IFRS filers return a clear "unsupported" signal rather than wrong numbers); XBRL-era history (~2009 onward). And when a company reorganizes under a new holding entity, SEC's ticker map points only at the successor CIK — the earlier years stay under the predecessor, so the error tells you and you pass cik= directly.

Tools

  • get_financials — normalized income statement + balance sheet + cash flow for one company and fiscal year, from SEC EDGAR XBRL. Supports as_of (point-in-time, as originally reported), include_provenance (per-value SEC accession, filed date, and direct EDGAR source URL), and include_ratios (margins, ROA/ROE, leverage).

  • get_financials_batch — the same, for up to 25 companies in one call (comma-separated tickers/CIKs). Per-symbol results; counts as a single quota unit, so one bad symbol never fails the batch.

  • list_filings — a company's recent SEC filings (newest first) from the EDGAR submissions index; filter by form (e.g. 10-K). Use it to discover which fiscal years are available before calling get_financials.

  • get_revisions — how a fiscal year's figures CHANGED across filings: every reported value with its filing date, form, SEC accession and EDGAR link, plus whether it was restated and by how much. Pfizer's FY2019 revenue was filed at $51.75B in 2020 and restated to $40.9B by 2022 — this is how you see that.

  • search_companies — find a ticker and CIK by ticker or company name, for when you have "Berkshire" and need BRK-B. Use it before the tools above, which all require an identifier.

  • get_usage — the key's monthly quota (tier, used, remaining, reset). Free to call; consumes no quota.

Errors surface the API's recovery_action hint, so agents self-correct.

Claude Desktop

Add to claude_desktop_config.json, then fully quit (Cmd+Q) and reopen Claude Desktop — the tools appear:

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

Then ask, e.g., "Get AAPL's FY2023 income statement, balance sheet, and cash flow with ratios." Swap in your real key for live data.

Codex

Add to ~/.codex/config.toml, then start codex — the tools appear:

[mcp_servers.datavidence-financials]
command = "uvx"
args = ["datavidence-financials"]
env = { FL_API_KEY = "sandbox_demo_key" }
# uvx downloads the package on first run; allow more than Codex's 10 s default.
startup_timeout_sec = 30

Swap in your real key for live data.

Or connect by URL instead (nothing to install; set DATAVIDENCE_API_KEY to your RapidAPI key):

[mcp_servers.datavidence-financials]
url = "https://mcp.financials.datavidence.ai/rapidapi/mcp"
bearer_token_env_var = "DATAVIDENCE_API_KEY"

Leave out bearer_token_env_var and use https://mcp.financials.datavidence.ai/mcp for the sample data.

Configuration (environment variables)

Variable

Default

Notes

FL_API_KEY

(none)

Your API key. sandbox_demo_key = no-signup trial (sample data).

FL_API_BASE_URL

https://api.financials.datavidence.ai

Point at a marketplace gateway for metered BYOK access.

FL_API_KEY_HEADER

X-API-Key

Header to send the key in (e.g. X-RapidAPI-Key for the RapidAPI gateway).

FL_API_TIMEOUT

30

Per-request timeout, in seconds.

Getting live data

The demo key returns sample data. For live figures, grab a key on RapidAPI: Free (1,500 calls/mo), Pro ($29 / 50k), Business ($99 / 300k). Full feature parity across tiers — they differ only by monthly call volume.

To use your RapidAPI key, set these three variables (in the env block of the Claude Desktop config, or the env table in Codex's config.toml):

FL_API_BASE_URL=https://datavidence-financials-api.p.rapidapi.com
FL_API_KEY_HEADER=X-RapidAPI-Key
FL_API_KEY=<your RapidAPI key>

Your key is on RapidAPI under your app's Authorization page, or in any code snippet on the API's page. Calls are metered by RapidAPI against your plan. With a RapidAPI key, get_usage shows your RapidAPI plan and its monthly limit; RapidAPI meters your calls, so check how many you've used in your RapidAPI dashboard.

Run from source

pip install -e .
FL_API_KEY=sandbox_demo_key python -m mcp_server.server   # stdio transport

Tests

pip install -e ".[dev]"
pytest

29 tests, no network and no API key needed. They call every tool through the MCP SDK with the HTTP layer stubbed, check that an API error reaches the model with its recovery hint, and check that each tool declares all four behaviour hints (read-only, non-destructive, idempotent, open-world).

Privacy Policy

The connector runs on your machine, has no telemetry and stores nothing. When a tool is called it sends two things to the Datavidence Financials API: the tool's arguments (for example a ticker, a CIK, a fiscal year or a company-name search) and your API key, in a request header. It does not see your files or the rest of your conversation.

  • Where it goes: https://api.financials.datavidence.ai by default. If you set FL_API_BASE_URL to the RapidAPI gateway, requests go through RapidAPI, under its own privacy policy.

  • What the API records: for each request, the endpoint, HTTP status, response time, timestamp and IP address, tied to a hash of the API key (never the key itself).

  • Retention: usage logs are kept for 12 months.

  • Sharing: not sold; shared only with the marketplace gateway you subscribed through and the infrastructure provider that hosts the service.

  • Contact: admin@datavidence.ai

Full policy: https://financials.datavidence.ai/privacy

Feedback

Found a company where the numbers come back wrong, or a field/tool you need? Open an issue — the normalization edge cases are exactly the feedback that makes this better, and I read every one.

License

MIT © 2026 Datavidence LLC — see LICENSE. The connector is open-source; the underlying Datavidence Financials API is a commercial service.

Available Tools

6 tools
get_financialsGet financial statementsA
Read-onlyIdempotent

Retrieve normalized US-GAAP financial statements (income statement, balance sheet, cash flow) for one company and fiscal year, from SEC EDGAR XBRL.

Identify the company by ticker OR cik. Use as_of (ISO YYYY-MM-DD) to get the figures as originally reported on that date — no look-ahead bias — for backtests. Set include_provenance=true to attach, for every value, the SEC accession, filed date, and a direct EDGAR source URL for citation. Set include_ratios=true for margins, ROA/ROE, and leverage derived from the same statements. Returns the normalized data object.

Inputs: year (required), cik, as_of, ticker, +2 more.

get_financials_batchGet financial statements for many companiesA
Read-onlyIdempotent

Retrieve normalized US-GAAP financials for MANY companies in one call — use this to compare peers or scan a set for a single fiscal year.

Pass companies as comma-separated tickers (e.g. "AAPL,MSFT,GOOGL") and/or ciks; up to 25 symbols total, all for the same year. as_of, include_provenance, and include_ratios behave as in get_financials and apply to every symbol. Each company returns its own result — either data or an error with a recovery hint — so one bad symbol never fails the batch. The whole call counts as a SINGLE request against your monthly quota, so prefer it over many get_financials calls when you need several companies.

Inputs: year (required), ciks, as_of, tickers, +2 more.

get_revisionsGet restatement historyA
Read-onlyIdempotent

Show how a company's reported figures for a fiscal year CHANGED across filings — as originally reported, then each restatement.

A company re-reports every fiscal year as a comparative in later filings, and when a number changes, that is a restatement. This returns the full series for each metric: every reported value with the date it was filed, the form (10-K/10-Q), the SEC accession and a direct EDGAR link, plus whether it was restated and by how much.

Use it to answer "has this been restated?", to show a figure's history, or to explain why a backtest on today's data would not match what an investor could have known at the time. Identify the company by ticker OR cik; narrow with metrics (comma-separated, e.g. "total_revenue,net_income") or omit for all. get_financials returns the LATEST reported figure; its as_of parameter returns the value as known on a date; this shows the whole series at once.

Inputs: year (required), cik, ticker, metrics.

get_usageCheck API usageA
Read-onlyIdempotent

Report the calling API key's current monthly quota: tier, monthly limit, requests used and remaining this billing month, and when it resets.

Free to call — it does NOT consume quota. Check it before a large batch or a long run so you can pace requests and avoid a hard rate-limit (429).

Inputs: no named parameters.

list_filingsList SEC filingsA
Read-onlyIdempotent

List a company's recent SEC filings (newest first) from the EDGAR submissions index — a lean company header plus filing rows.

Identify the company by ticker OR cik. Optionally filter by form (e.g. "10-K", prefix-matched so it includes amendments like "10-K/A") and cap the number of rows with limit (1-100). Use this to discover which fiscal years or filings are available before calling get_financials.

Inputs: cik, form, limit, ticker.

search_companiesSearch companiesA
Read-onlyIdempotent

Find a company's ticker and CIK by ticker or company name.

Use this FIRST whenever you have a company name but not its ticker or CIK — every other tool needs one of those. Searches SEC's master list: "berkshire" returns BRK-B with its CIK, "mobil" returns XOM.

Ranked so the obvious answer wins (an exact ticker beats a company whose name merely contains the text). limit caps the number of matches (1-25).

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.7/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: company lookup, filing discovery, single financials, batch financials, restatement history, and quota monitoring. The descriptions explicitly disambiguate the most similar tools, such as get_financials versus get_revisions.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern: get_financials, list_filings, get_financials_batch, get_revisions, search_companies, get_usage. The batch variant is clearly a modifier of get_financials rather than a breaking convention.

    Tool Count5/5

    Six tools is well-scoped for a financial data server. Each tool earns its place: lookup, filing discovery, single retrieval, batch retrieval, revision history, and usage monitoring, with no meaningful redundancy.

    Completeness5/5

    The toolset covers the full natural workflow: resolve identifiers with search_companies, discover available filings with list_filings, retrieve financials individually or in batch, inspect restatements with get_revisions, and track quota with get_usage. No critical dead ends exist within the stated SEC EDGAR normalized-financials domain.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Provides access to SEC EDGAR financial data, enabling AI agents to fetch company filings, financial metrics, and narrative sections. It supports natural-language metric searching and extracts structured data from 10-K, 10-Q, and 8-K reports.
      6
      125 PyPI
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Give your AI agent live SEC EDGAR data: company financials, insider trades, 8-K events, 13F holdings, and the raw filings stream — all normalized to clean JSON, every number traceable back to its sec.gov source filing.
      8
      43 PyPI
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Standardizes XBRL financial data from US SEC and European ESEF filings for LLM agents, enabling querying normalized financial facts like revenue and total assets across issuers and taxonomies.
      21
      39 PyPI
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to query US public company financial data from SEC filings, with tools for resolving tickers, listing filings, retrieving financial concepts, comparing companies, extracting filing sections, and full-text search. It surfaces data ambiguities like tag variations, restatements, and fiscal-year misalignment rather than hiding them.
      6
      MIT