SET-MCP
Access financial statements, including income, balance sheets, and cash flow, for companies listed on the Securities Exchange of Thailand (SET).
SET-MCP
SET-MCP is a Python package that provides tools for serving Model Context Protocol which can access the Securities Exchange of Thailand (SET). It allows AI agents to retrieve comprehensive financial statements including income statements, balance sheets, and cash flow statements for listed companies.
Features
- Retrieve financial statements for SET-listed companies
- Support for multiple financial statement types:
- Income Statement
- Balance Sheet
- Cash Flow Statement
- Historical data retrieval with customizable date ranges
- Command-line interface for easy integration
- FastMCP integration for enhanced functionality
Installation
The package requires Python 3.11 or higher. You can install it using pip:
pip install set-mcp
Installing via Smithery
To install set-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install set-mcp --client claude
Usage
Command Line Interface
The package provides a command-line interface for easy access to financial data:
set-mcp --transport stdio
Using with uvx
Run
uvx set-mcp
Using with pipx
pipx install set-mcp
pipx run set-mcp
MCP.json example
{
"mcpServers": {
"set_mcp": {
"command": "/path/to/bin/uvx", // Edit to your uvx path
"args": [
"set-mcp"
],
}
}
}
Vercel
Coming soon
Available options:
--port: Port to listen on for SSE (default: 8000)--host: Host to listen on (default: 0.0.0.0)--transport: Transport type (choices: stdio, sse, default: stdio)
Note: SSE is not yet implemented
Python API
You can also use the package programmatically in your Python code:
from set_mcp import get_financial_statement
# Get financial statements for a specific company
result = await get_financial_statement(
symbol="PTT", # Company symbol
from_year=2023,
to_year=2024
)
Development
Setup Development Environment
- Clone the repository:
git clone https://github.com/yourusername/set-mcp.git
cd set-mcp
- Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
- Install development dependencies:
pip install -e ".[dev]"
Running Tests
python test_client.py
The output should be no error
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Author
- Prem Chotipanit ([email protected] | [email protected])
相關伺服器
PostgreSQL
Provides read-only access to PostgreSQL databases, allowing LLMs to inspect schemas and execute queries.
Pylar
Build custom MCP tools on any datasource and ship them to any agent builder from one control plane—using only SQL and a secure link.
FHIR MCP Server by CData
A read-only MCP server for FHIR, enabling LLMs to query live FHIR data. Requires the CData JDBC Driver for FHIR.
Azure Data Explorer
An MCP server for integrating with Azure Data Explorer, allowing for data querying and management.
mcp-1c
1C:Enterprise integration — metadata, BSL code search, queries, event log, syntax reference. One Go binary, zero dependencies.
Noves MCP Server
Access blockchain transaction data in natural language, providing human-readable descriptions for AI assistants.
Dremio
Integrate Large Language Models (LLMs) with Dremio, a data lakehouse platform.
Generect MCP
Generect MCP connects your live lead database directly to AI models like OpenAI or Claude without exports or delays. It streams enriched, up-to-date contact data (titles, firmographics, signals) straight into prompts so LLMs can personalize, score, and recommend leads automatically in real time.
CData Adobe Analytics
A read-only MCP server to query live Adobe Analytics data. Requires the CData JDBC Driver for Adobe Analytics.
Michelin MCP
Access structured Michelin restaurant data, including cities, countries, cuisines, awards, and facilities.