Finance MCP Server
An MCP server for retrieving financial data using the financialdatasets API.
Building a Finance agent with MCP
See Full Video:
Overview
This project demonstrates the use of a Model Context Protocol (MCP) server for retrieving financial data. The MCP server is integrated with Agno and Smol Agent to showcase its versatility in handling multiple agentic frameworks in standardized way.
-
MCP Server (Finance):
- This server is created using
financialdatasets apifetch financial information of companies - Standardizes interactions with external financial data sources using MCP.
- This server is created using
-
Agentic Framework Integration
- Integrated mcp server with Agno and Smol Agent.
- MCP creates a universal standard for all agentic workflows.
Features
- MCP enables AI applications to access diverse data sources and tools using a consistent protocol, streamlining the development process.
- AI applications (clients) communicate with MCP servers that expose specific capabilities, such as data access or function execution
- MCP allows AI models to retrieve up-to-date information and perform actions based on real-time data, enhancing their responsiveness and accuracy .
Getting Started
- Clone the repository:
git clone https://github.com/Ihtishammehmood/Finance_MCP-Server.git
- Add Groq and Financial Datasets APi to .env:
GROQ_API_KEY = "Place your GROQ API key here"
FINANCIAL_DATASETS_API_KEY = "Place your Financial Datasets API key here"
- Install UV package Manager
pip install uv
- Create Virtual Environment
uv venv
- Activate virtual Environment:
.venv\Scripts\activate
- Install dependencies
uv add -r requirements.txt
- Start Agno and Smol Agent integrations:
uv run agno_agent.py
Initialize MCP Inspector
- Run
mcp dev server.pyin Terminal
Add MCP server in IDE
{
"mcpServers": {
"stockTools": {
"command": "uv",
"args": [
"--directory",
"Absolute path to server.py file directory",
"run",
"server.py"
]
}
}
}
License
This project is licensed under the MIT License - see the LICENSE file for details.
Related Servers
MCP Remote with Okta/Adobe IMS Authentication
A remote MCP server that uses Adobe IMS/Okta for authentication.
Strava MCP Server
A server that connects to the Strava API, allowing language models to access Strava data and features.
EdgeOne Geo Location
Provides geolocation data using EdgeOne Pages Functions.
Cloudflare MCP Server
A template for deploying a remote MCP server on Cloudflare Workers without authentication.
Keycloak MCP Server
Administer Keycloak users and realms using a Model Context Protocol server.
AWS Security MCP
An MCP server that enables AI assistants to interact with AWS security services.
EdgeOne Geo Location Service
Provides user geolocation data via Tencent EdgeOne Pages Functions, enabling large language models to access location information.
Binance MCP Server
Interact with the Binance API to view portfolios, convert tokens, and execute trades with minimal market impact.
AKS-MCP
Enables AI assistants to interact with Azure Kubernetes Service (AKS) clusters.
CData PingOne
A read-only MCP server that allows LLMs to query live PingOne data. Requires a separate CData JDBC Driver for PingOne.