Finance Toolkit
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Description from the maker (original English)
Normalized US-GAAP financial statements & fundamentals from SEC EDGAR, as MCP tools for LLM agents.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
FL_API_KEY, FL_API_BASE_URL, FL_API_KEY_HEADER, FL_API_TIMEOUTValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"datavidence-financials": {
"command": "uvx",
"args": [
"datavidence-financials"
],
"env": {
"FL_API_KEY": "your-value",
"FL_API_BASE_URL": "your-value",
"FL_API_KEY_HEADER": "your-value",
"FL_API_TIMEOUT": "your-value"
}
}
}
}Run this in your terminal
claude mcp add datavidence-financials --env FL_API_KEY=your-value --env FL_API_BASE_URL=your-value --env FL_API_KEY_HEADER=your-value --env FL_API_TIMEOUT=your-value -- uvx datavidence-financialsFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"datavidence-financials": {
"command": "uvx",
"args": [
"datavidence-financials"
],
"env": {
"FL_API_KEY": "your-value",
"FL_API_BASE_URL": "your-value",
"FL_API_KEY_HEADER": "your-value",
"FL_API_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"datavidence-financials": {
"type": "stdio",
"command": "uvx",
"args": [
"datavidence-financials"
],
"env": {
"FL_API_KEY": "your-value",
"FL_API_BASE_URL": "your-value",
"FL_API_KEY_HEADER": "your-value",
"FL_API_TIMEOUT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
FL_API_BASE_URL envFL_API_KEY_HEADER envFL_API_TIMEOUT envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain datavidence.ai (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: FL_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.5) reached the registry 44 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Finance Toolkit, SolidInvoice, Korea Tax Calculator
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
500+ transparent financial methods calculated from raw statements, not third-party endpoints.
Create and send invoices and quotes, manage clients, and track payments in SolidInvoice.
Korean tax calculation and tax-audit judgment MCP: 96 tools with statutory citations.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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).
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.
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.
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
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.
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.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.
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).10-K). Use it to discover which fiscal years are available before calling get_financials.BRK-B. Use it before the tools above, which all require an identifier.Errors surface the API's recovery_action hint, so agents self-correct.
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.
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" }
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.
| 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. |
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 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.
pip install -e .
FL_API_KEY=sandbox_demo_key python -m mcp_server.server # stdio transport
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).
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.
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.Full policy: https://financials.datavidence.ai/privacy
Found a company where the numbers come back wrong, or a field/tool you need? [Open an issue](https://github.com/datavidence/datavidence-financials-mcp/issues) — the normalization edge cases are exactly the feedback that makes this better, and I read every one.
ai.datavidence/datavidence-financialsSECURITY.md to report a vulnerability privately.MIT © 2026 Datavidence LLC — see LICENSE. The connector is open-source; the underlying Datavidence Financials API is a commercial service.