Server facts
Financial Datasets MCP Server
Project
- Author
- financial-datasets
- Repository
- github.com/financial-datasets/mcp-server
- Website
- www.financialdatasets.ai/
- License
- MIT
- Category
- Finance & Commerce
Tech
- Runtime / language
- pythonPython
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 2,307
- Last commit
- Data as of
Tags
- Company Statements
- Crypto
- Financial Data
- Market News
- Stock Prices
Overview
Financial Datasets MCP Server brings market and company information from Financial Datasets into compatible AI assistants. Its tool list covers income statements, balance sheets, and cash flow statements, giving an assistant access to several distinct views of a company's reported finances. Separate operations retrieve current stock quotes, historical stock prices, and company news. Cryptocurrency support includes discovering available tickers and requesting current or historical prices. The README presents these as retrieval tools for Claude and other assistants; it does not describe order placement, portfolio execution, or an investment recommendation engine.
The implementation runs locally with Python 3.10 or newer and the uv package manager. Setup involves cloning the repository, creating a virtual environment, installing the listed MCP and HTTP dependencies, and supplying a Financial Datasets API key in an environment file. The documented launch command runs server.py through uv. Claude Desktop configuration uses the executable's absolute path and the project's directory so the client can start the correct local process. After restarting the desktop client, its tool menu should expose the financial operations. This is a focused integration for users who want an assistant to retrieve specific market datasets rather than manually transfer results between an external data service and a conversation. Coverage limits, pricing, and request quotas are not stated in the supplied README.
Install & configure
Requirements
- Python 3.10 or newer
- uv package manager
- A local clone of the repository
- The documented mcp[cli] and httpx dependencies
- A Financial Datasets API key
uv run server.pyRun from the cloned project after dependency and environment setup. For Claude Desktop, the README shows an absolute uv path and an explicit project directory.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server": {
"command": "uv",
"args": [
"run",
"server.py"
],
"env": {
"FINANCIAL_DATASETS_API_KEY": "<Financial Datasets API key>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server": {
"command": "uv",
"args": [
"run",
"server.py"
],
"env": {
"FINANCIAL_DATASETS_API_KEY": "<Financial Datasets API key>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"server.py"
],
"env": {
"FINANCIAL_DATASETS_API_KEY": "<Financial Datasets API key>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server": {
"command": "uv",
"args": [
"run",
"server.py"
],
"env": {
"FINANCIAL_DATASETS_API_KEY": "<Financial Datasets API key>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"mcp-server": {
"type": "stdio",
"command": "uv",
"args": [
"run",
"server.py"
],
"env": {
"FINANCIAL_DATASETS_API_KEY": "<Financial Datasets API key>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| get_income_statements | Retrieve a company’s income statement data. |
| get_balance_sheets | Retrieve company balance sheet records. |
| get_cash_flow_statements | Fetch a company’s cash flow statement records. |
| get_current_stock_price | Read the latest available quote for a company. |
| get_historical_stock_prices | Fetch stock price records over time. |
| get_company_news | Retrieve news associated with a company. |
| get_available_crypto_tickers | List cryptocurrency ticker symbols available from the service. |
| get_crypto_prices | Retrieve cryptocurrency historical price data as described in the README. |
| get_historical_crypto_prices | Fetch a cryptocurrency price history. |
| get_current_crypto_price | Read the latest available cryptocurrency price. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Retrieve a company’s financial statements for an assistant-led review.
- Compare current and historical stock prices.
- Collect company-specific market news.
- Discover supported cryptocurrency tickers and retrieve price histories.
Strengths
- Exposes financial statements, prices, and company news in one MCP integration.
- Includes both equity and cryptocurrency retrieval tools.
- Provides a concrete local Python setup and Claude Desktop example.
Limitations
- Requires a Financial Datasets API key and local Python setup.
- Coverage, pricing, and request quotas are Not stated in the README.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
