Lets an AI assistant query financial data including quotes, company profiles, financial statements, and market indicators through 240 API endpoints.
Also known as daxm/fmpsdk, fmpsdk, fmpsdk-mcp
- Stars
- 214
- Tools
- 13
- Downloads, 30 days
- 112
- Latest version
- 20260829.1
- Last commit
- Aug 29, 2026
- License
- BSD-3-Clause
What is Financial Modeling Prep MCP?
Financial Modeling Prep lets an AI assistant query financial data including quotes, company profiles, financial statements, and market indicators through 240 API endpoints. It exposes 13 tools, such as get_quote, get_company_profile, get_income_statement.
Summary generated from the project's README
About Financial Modeling Prep MCP server
Financial analysts and developers can access a massive repository of market intelligence by connecting their AI assistants to this server. It provides a direct interface to approximately 240 API endpoints covering company fundamentals, real-time quotes, financial statements, and various market indicators. Users can retrieve data ranging from income statements and balance sheets to cryptocurrency prices, forex rates, and even congressional trading activity.
To use this server with clients like Claude Desktop or Claude Code, you must provide a valid Financial Modeling Prep API key via an environment variable. The server is designed to work with different subscription tiers, including Free, Starter, Premium, and Ultimate plans. If a requested tool exceeds your current plan's permissions, the server raises a specific error rather than returning empty data. This allows the AI to understand exactly why certain financial metrics or historical charts are unavailable.
What you can do with it
- 1Analyze company financial healthAsk the AI to retrieve and compare income statements or balance sheets for specific stock symbols.
- 2Monitor real-time market movementsRequest current stock quotes or aftermarket pricing to track recent market activity.
- 3Track institutional and insider activityHave the assistant look up SEC filings or Form 13F institutional ownership data.
- 4Perform broad market screeningUse the assistant to find companies within specific sectors or industries using the screener.
Written from the project's README. Every use case is checked against a quote from it.
How to install Financial Modeling Prep MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Financial Modeling Prep MCP in Claude Code
$ claude mcp add --env 'FMP_API_KEY=<YOUR_FMP_API_KEY>' fmpsdk -- uvx fmpsdk-mcpInstall Financial Modeling Prep MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"fmpsdk": {
"command": "uvx",
"args": [
"fmpsdk-mcp"
],
"env": {
"FMP_API_KEY": "<YOUR_FMP_API_KEY>"
}
}
}
}Install Financial Modeling Prep MCP in VS Code
.vscode/mcp.json
{
"servers": {
"fmpsdk": {
"type": "stdio",
"command": "uvx",
"args": [
"fmpsdk-mcp"
],
"env": {
"FMP_API_KEY": "<YOUR_FMP_API_KEY>"
}
}
}
}Install Financial Modeling Prep MCP in VS Code CLI
$ code --add-mcp '{"name":"fmpsdk","type":"stdio","command":"uvx","args":["fmpsdk-mcp"],"env":{"FMP_API_KEY":"<YOUR_FMP_API_KEY>"}}'Install Financial Modeling Prep MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"fmpsdk": {
"command": "uvx",
"args": [
"fmpsdk-mcp"
],
"env": {
"FMP_API_KEY": "<YOUR_FMP_API_KEY>"
}
}
}
}Install Financial Modeling Prep MCP in Codex
$ codex mcp add fmpsdk --env 'FMP_API_KEY=<YOUR_FMP_API_KEY>' -- uvx fmpsdk-mcpInstall Financial Modeling Prep MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.fmpsdk] command = "uvx" args = ["fmpsdk-mcp"] [mcp_servers.fmpsdk.env] FMP_API_KEY = "<YOUR_FMP_API_KEY>"
Install Financial Modeling Prep MCP in Gemini CLI
$ gemini mcp add -s user -e 'FMP_API_KEY=<YOUR_FMP_API_KEY>' fmpsdk uvx -- fmpsdk-mcpInstall Financial Modeling Prep MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"fmpsdk": {
"command": "uvx",
"args": [
"fmpsdk-mcp"
],
"env": {
"FMP_API_KEY": "<YOUR_FMP_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for fmpsdk-mcp 20260829.1 in an isolated container with no network and no keys. It answered and listed 13 tools.
Financial Modeling Prep MCP tools 13
Read from the server with tools/listget_quoteFull real-time quote for one symbol (equity, index, commodity, crypto, or forex pair): price, change, day/52-week range, volume, market cap, 50/200-day averages.
get_company_profileCompany profile: price and market cap, identifiers (CIK/ISIN/CUSIP), sector and industry, headquarters, leadership, description, exchange.
get_income_statementIncome statement (revenue, expenses, net income) for one company. period: "annual" or "quarter". limit: how many periods, newest first.
get_balance_sheetBalance sheet (assets, liabilities, equity) for one company. period: "annual" or "quarter". limit: how many periods, newest first.
get_cash_flowCash flow statement (operating, investing, financing) for one company. period: "annual" or "quarter". limit: how many periods, newest first.
get_key_metricsPer-period key metrics: valuation multiples, per-share figures, returns on capital, margins — FMP-computed from the statements.
get_financial_ratiosPer-period financial ratios: liquidity, leverage, efficiency, profitability, and valuation — FMP-computed from the statements.
get_historical_pricesDaily close price and volume for one symbol between two dates (YYYY-MM-DD). Leave dates unset for FMP's default recent window. Long ranges are returned page by page — see the response's `note`.
search_symbolResolve a ticker symbol from a name or fragment (e.g. "apple" -> AAPL).
get_stock_newsRecent news articles for one or more symbols (comma-separated, e.g. "AAPL,MSFT"): headline, publisher, url, published date, snippet.
list_fmp_endpointsFind FMP endpoints beyond the curated tools. `query` is a substring match over name/group/summary; `group` filters to one category (e.g. "congress", "institutional_ownership"); `free_only` drops endpoints that need a paid FMP plan. Returns name, group, plan tier ("Free"/"Starter"/ "Premium"/"Ultimate"/"Add-on"), and one-line summary — pass a name to `describe_fmp_endpoint` for the full signature.
describe_fmp_endpointFull detail for one endpoint: call signature, every parameter, return type, plan tier, FMP wire path, and the complete docstring. Use before `call_fmp_endpoint` so the arguments are right.
| get_quote | Full real-time quote for one symbol (equity, index, commodity, crypto, or forex pair): price, change, day/52-week range, volume, market cap, 50/200-day averages. | |
| get_company_profile | Company profile: price and market cap, identifiers (CIK/ISIN/CUSIP), sector and industry, headquarters, leadership, description, exchange. | |
| get_income_statement | Income statement (revenue, expenses, net income) for one company. period: "annual" or "quarter". limit: how many periods, newest first. | |
| get_balance_sheet | Balance sheet (assets, liabilities, equity) for one company. period: "annual" or "quarter". limit: how many periods, newest first. | |
| get_cash_flow | Cash flow statement (operating, investing, financing) for one company. period: "annual" or "quarter". limit: how many periods, newest first. | |
| get_key_metrics | Per-period key metrics: valuation multiples, per-share figures, returns on capital, margins — FMP-computed from the statements. | |
| get_financial_ratios | Per-period financial ratios: liquidity, leverage, efficiency, profitability, and valuation — FMP-computed from the statements. | |
| get_historical_prices | Daily close price and volume for one symbol between two dates (YYYY-MM-DD). Leave dates unset for FMP's default recent window. Long ranges are returned page by page — see the response's `note`. | |
| search_symbol | Resolve a ticker symbol from a name or fragment (e.g. "apple" -> AAPL). | |
| get_stock_news | Recent news articles for one or more symbols (comma-separated, e.g. "AAPL,MSFT"): headline, publisher, url, published date, snippet. | |
| list_fmp_endpoints | Find FMP endpoints beyond the curated tools. `query` is a substring match over name/group/summary; `group` filters to one category (e.g. "congress", "institutional_ownership"); `free_only` drops endpoints that need a paid FMP plan. Returns name, group, plan tier ("Free"/"Starter"/ "Premium"/"Ultimate"/"Add-on"), and one-line summary — pass a name to `describe_fmp_endpoint` for the full signature. | |
| describe_fmp_endpoint | Full detail for one endpoint: call signature, every parameter, return type, plan tier, FMP wire path, and the complete docstring. Use before `call_fmp_endpoint` so the arguments are right. |
Show all 13 toolsShow fewer tools
call_fmp_endpointInvoke any FMP endpoint by its fmpsdk method name. `params` is a dict of that method's arguments (see `describe_fmp_endpoint`). Large list results are paged: the response carries `page`, `total`, `more`, and a `note` on how to get the rest. `bulk` and whole-asset-class batch endpoints are refused here — use the fmpsdk library directly for those.
| call_fmp_endpoint | Invoke any FMP endpoint by its fmpsdk method name. `params` is a dict of that method's arguments (see `describe_fmp_endpoint`). Large list results are paged: the response carries `page`, `total`, `more`, and a `note` on how to get the rest. `bulk` and whole-asset-class batch endpoints are refused here — use the fmpsdk library directly for those. |
Configuration
FMP_API_KEYRequiredSecretFinancial Modeling Prep API key (https://site.financialmodelingprep.com/developer/docs)
| Name | Description | |
|---|---|---|
| FMP_API_KEY | Financial Modeling Prep API key (https://site.financialmodelingprep.com/developer/docs) | RequiredSecret |
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachabledaxm/fmpsdk is public and reachablegithub.com/daxm/fmpsdk ↗Pass
- Package names this repository as its sourcefmpsdk-mcp names daxm/fmpsdk as sourcepypi.org/project/fmpsdk-mcp/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for fmpsdk-mcppypi.org/project/fmpsdk-mcp/ ↗Pass
- Open source license (OSI)BSD-3-Clausespdx.org/licenses/BSD-3-Clause.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-29github.com/daxm/fmpsdk ↗Pass
- OpenSSF ScorecardOpenSSF Scorecard 2.9 / 10; weakest: Code-Review 0, Dangerous-Workflow 0, Token-Permissions 0scorecard.dev/viewer/?uri=github.com/daxm/fmpsdk ↗Partial 4/15
- Package name not close to a popular packageNo popular package one edit away from fmpsdk-mcpPass
- No critical advisory in the package or its dependencies73 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model13 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubFMP SDK
The idea behind this project is to provide a 'one-stop-shop' to the API endpoints provided by Financial Modeling Prep (FMP).
A personal note to you: my apologies for letting this package get so out of date. FMP kept
reshuffling its API, then I had a personal issue delay me further. Things are back on track now.
Because of that gap, roughly half of this package's old methods had gone defunct against FMP's
current API, so rather than patch around that I rebuilt it from scratch against FMP's stable/
API. If you're on 20250102.0 or earlier you're on the old, pre-rewrite methods; anything newer
uses the schema described below. Old releases are yanked from PyPI (a plain pip install fmpsdk
now always gets the rewrite), but still installable if you pin one explicitly, e.g.
pip install fmpsdk==20250102.0 — note that won't actually restore functionality, though: FMP
sunset the legacy /api/v3/ API those old methods called entirely on 2025-08-31, so a pinned old
version installs fine but its calls will fail regardless. It's there for compatibility with
existing pinned requirements files while you migrate, not as a way to keep avoiding the rewrite.
What's covered
29 data groups, ~240 methods total, each reachable both as client.<method>(...) and grouped
under a matching namespace, e.g. client.statements.income_statement(...):
- Company & fundamentals — profile, executives, M&A, DCF valuation, financial statements/ ratios/growth (income, balance sheet, cash flow — as-reported, TTM, and growth variants)
- Market data — real-time & aftermarket quotes, historical price charts, technical indicators
- Reference & screening — symbol/CIK/CUSIP/ISIN search, the company screener, sector/ industry/exchange directories
- Calendars & events — earnings, dividends, splits, IPOs, the economic calendar
- Ownership & compliance — insider trades, Form 13F institutional ownership, SEC filings, ESG disclosures
- Alternative markets — crypto, forex, commodities, indexes, ETFs & mutual funds
- Sentiment & analysis — analyst grades/price targets, TipRanks ratings, congressional trading, market movers
- Bulk downloads — whole-universe data dumps, one call instead of one per symbol
Every method's own docstring says which FMP plan tier it needs (Free/Starter/Premium/
Ultimate) — see Pricing tiers below. One exception: the 7
client.tipranks methods are implemented and unit-tested but untested against a real
response — see that section for why.
How to Use
- Requires Python 3.9+. Install the package:
pip install fmpsdk python-dotenv(python-dotenvis optional — it's just how the example below loads your API key from a.envfile). - Create a
.envfile and put your API key in it. Inside.env:FMP_API_KEY='blah' - Build a
Clientand call methods on it, grouped by data category — e.g.client.company.profile(symbol="AAPL"),client.statements.income_statement(symbol="AAPL"). - The return from a method call is almost always a list of dictionaries. It is up to you to parse it.
Example code
#!/usr/bin/env python3
from dotenv import load_dotenv
import fmpsdk
# Actual API key is stored in a .env file. Not good to store API key directly in script.
load_dotenv()
client = fmpsdk.Client() # reads FMP_API_KEY from the environment
# Company Valuation Methods
symbol = "AAPL"
print(f"Company Profile: {client.company.profile(symbol=symbol)}")
# Every non-2xx FMP response raises a typed exception instead of returning
# None or an error-shaped dict, so a plan-gated or bad-key call is obvious:
try:
client.statements.income_statement_ttm(symbol=symbol)
except fmpsdk.FMPPlanLimitError:
print("Your FMP plan doesn't cover this endpoint — check its docstring for which tier does.")
except fmpsdk.FMPAuthenticationError:
print("Check your FMP_API_KEY.")
One naming quirk worth knowing up front: client.quote is the namespace for the whole quote
group (client.quote.aftermarket_quote(...), client.quote.batch_quote(...), etc.), so it
shadows the top-level quote() method of the same name — call that one as
client.quote.quote(symbol="AAPL").
Pricing tiers
FMP's plans form a ladder — Free, Starter, Premium, Ultimate — and each one adds more
endpoints on top of the last. A call your plan doesn't cover raises
fmpsdk.FMPPlanLimitError rather than returning data. There's no single tier table to keep
in sync here — instead, every group module's docstring (e.g. fmpsdk/endpoints/search.py)
and every method's own docstring says plainly which tier it needs, right next to the code
that calls it, verified live against a real key at every tier from Free through Ultimate.
Check those, or just try the call and catch FMPPlanLimitError.
One exception, outside that ladder entirely: client.tipranks's 7 methods. They still
402 even on Ultimate — FMP's own error message says why: TipRanks data needs a separate
paid add-on ("TipRanks data boost"), bought independently of the four plan tiers above. We
haven't purchased it, so these 7 methods are implemented and unit-tested (mocked) but
never verified against a real response — treat them as unverified rather than
confirmed-working. If you have that add-on and hit a bug in one of them, a PR with the fix
(and what the real response actually looks like) is welcome.
MCP server & OpenAPI spec
mcp/ — a Model Context Protocol
server, published separately as fmpsdk-mcp (so
pip install fmpsdk never pulls in fastmcp). Lets an AI assistant (Claude Code, Claude
Desktop, …) query FMP through this library: 10 curated tools for the common asks (quotes,
profiles, statements, ratios, price history, news) plus discovery tools that reach all
~240 methods at runtime. With uv:
claude mcp add fmpsdk -s user -e FMP_API_KEY=your-key -- uvx fmpsdk-mcp
See mcp/README.md for the Claude Desktop config, the full tool list, and
development setup.
openapi.json — an OpenAPI 3.1 description of the same API surface.
FMP publishes no OpenAPI/Swagger document; this file is generated by introspecting this
library's source (python tools/gen_openapi.py), not fetched from or endorsed by FMP.
Contributing
See CONTRIBUTING.md — dev setup, the unit/live/ultimate test tiers, and
specifically how to verify and PR a fix for the untested tipranks methods above.
License
BSD 3-Clause — see LICENSE.md.
Attribution
Special thanks to the following people who have pitched in on this project! Open source works thanks to people who jump in and help! These are this project's stars. Thank you.
- Ken Caruso
- iforgotmypass
- Ivelin Ivanov
- Claude Code
Financial Modeling Prep MCP questions
How do I add Financial Modeling Prep MCP to Claude Code?
Run claude mcp add --env 'FMP_API_KEY=<YOUR_FMP_API_KEY>' fmpsdk -- uvx fmpsdk-mcp in your terminal. Add --scope user to make it available in every project.
How do I add Financial Modeling Prep MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Financial Modeling Prep MCP provide?
It exposes 13 tools, including get_quote, get_company_profile, get_income_statement, get_balance_sheet, get_cash_flow.
How do I install the MCP server?
You can add it to Claude using uvx with the command: claude mcp add fmpsdk -s user -e FMP_API_KEY=your-key -- uvx fmpsdk-mcp
What happens if my API plan doesn't support a specific endpoint?
The library will raise an FMPPlanLimitError instead of returning data.
Are the TipRanks methods verified to work?
No, the 7 TipRanks methods are implemented and unit-tested but have not been verified against a real response.