
A Model Context Protocol Server to help your LLM access financial data
A Model Context Protocol Server to help your LLM access financial data
·
This is a MCP server that helps your MCP client/LLM get access to financial data like stock price, company info, and company news.
It is powered by the yfinance Python library and MarketAux API.
curl -LsSf https://astral.sh/uv/install.sh | shpowershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Make sure to restart your terminal afterwards to ensure that the uv command gets picked up.
Now, let’s create and set up our project:
git clone [email protected]:nimitmk7/mcp-finance.git
# Create .env file for your API keys
cp .env.example .env
# Set API key in .env
MARKETAUX_API_KEY=your-marketaux-api-keyIf you are using Claude Desktop Client, you can go to Settings -> Developer, and press on the button 'Edit Config'. It will open claude_desktop_config.json. Put the following configuration with your relevant details in the file:
{
"mcpServers": {
"mcp-finance": {
"command": "/Users/<username>/.local/bin/uv",
"args": [
"--directory",
"/Users/<username>/<path-to-dir>/mcp-finance",
"run",
"mcp_finance.py"
]
}
}
}{
"mcpServers": {
"mcp-finance": {
"command": "C:\\Users\\<username>\\.local\\bin\\uv.exe",
"args": [
"--directory",
"C:\\Users\\<username>\\<path-to-dir>\\mcp-finance",
"run",
"mcp_finance.py"
]
}
}
}If you already have some MCP servers, just add the mcp-finance config in the list of configs of MCP servers.
Restart the Claude Desktop client after these steps.
Try asking Claude questions like:
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add mcp-finance -- /Users/<username>/.local/bin/uv --directory /Users/<username>/<path-to-dir>/mcp-finance run mcp_finance.py{
"mcpServers": {
"mcp-finance": {
"args": [
"--directory",
"/Users/<username>/<path-to-dir>/mcp-finance",
"run",
"mcp_finance.py"
],
"command": "/Users/<username>/.local/bin/uv"
}
}
}code --add-mcp '{"name":"mcp-finance","args":["--directory","/Users/<username>/<path-to-dir>/mcp-finance","run","mcp_finance.py"],"command":"/Users/<username>/.local/bin/uv"}'[mcp_servers.mcp-finance]
command = "/Users/<username>/.local/bin/uv"
args = ["--directory", "/Users/<username>/<path-to-dir>/mcp-finance", "run", "mcp_finance.py"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/introduction to learn what the "Introduction" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/introduction)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "introduction" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.