Skip to main content

MCP server for AKShare financial data

Project description

AKShare MCP Server

A Model Context Protocol (MCP) server that provides financial data analysis capabilities using the AKShare library.

Features

  • Access to Chinese and global financial market data through AKShare
  • Integration with Claude Desktop via MCP protocol
  • Support for various financial data queries and analysis

Installation

Using uv (recommended)

# Clone the repository
git clone https://github.com/yourusername/akshare_mcp_server.git
cd akshare_mcp_server

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies with uv
uv pip install -e .

Using pip

# Clone the repository
git clone https://github.com/yourusername/akshare_mcp_server.git
cd akshare_mcp_server

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -e .

Usage

Running the server

# Activate the virtual environment
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Run the server
python run_server.py

Integrating with Claude Desktop

  1. Add the following configuration to your Claude Desktop configuration:
"mcpServers": {
    "akshare-mcp": {
        "command": "uv",
        "args": [
            "--directory",
            "/path/to/akshare_mcp_server",
            "run",
            "akshare-mcp"
        ],
        "env": {
            "AKSHARE_API_KEY": "<your_api_key_if_needed>"
        }
    }
}
  1. Restart Claude Desktop
  2. Select the AKShare MCP server from the available tools

Available Tools

The AKShare MCP server provides the following tools:

  • Stock data queries
  • Fund data queries
  • Bond data queries
  • Futures data queries
  • Forex data queries
  • Macroeconomic data queries
  • And more...

Adding a New Tool

To add a new tool to the MCP server, follow these steps:

  1. Add a new API function in src/mcp_server_akshare/api.py:

    async def fetch_new_data_function(param1: str, param2: str = "default") -> List[Dict[str, Any]]:
        """
        Fetch new data type.
        
        Args:
            param1: Description of param1
            param2: Description of param2
        """
        try:
            df = ak.akshare_function_name(param1=param1, param2=param2)
            return dataframe_to_dict(df)
        except Exception as e:
            logger.error(f"Error fetching new data: {e}")
            raise
    
  2. Add the new tool to the enum in src/mcp_server_akshare/server.py:

    class AKShareTools(str, Enum):
        # Existing tools...
        NEW_TOOL_NAME = "new_tool_name"
    
  3. Import the new function in src/mcp_server_akshare/server.py:

    from .api import (
        # Existing imports...
        fetch_new_data_function,
    )
    
  4. Add the tool definition to the handle_list_tools() function:

    types.Tool(
        name=AKShareTools.NEW_TOOL_NAME.value,
        description="Description of the new tool",
        inputSchema={
            "type": "object",
            "properties": {
                "param1": {"type": "string", "description": "Description of param1"},
                "param2": {"type": "string", "description": "Description of param2"},
            },
            "required": ["param1"],  # List required parameters
        },
    ),
    
  5. Add the tool handler in the handle_call_tool() function:

    case AKShareTools.NEW_TOOL_NAME.value:
        param1 = arguments.get("param1")
        if not param1:
            raise ValueError("Missing required argument: param1")
        
        param2 = arguments.get("param2", "default")
        
        result = await fetch_new_data_function(
            param1=param1,
            param2=param2,
        )
    
  6. Test the new tool by running the server and making a request to the new tool.

Development

# Install development dependencies
uv pip install -e ".[dev]"

# Run tests
pytest

Docker

You can also run the server using Docker:

# Build the Docker image
docker build -t akshare-mcp-server .

# Run the Docker container
docker run -p 8000:8000 akshare-mcp-server

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

akshare_mcp_server-0.1.1.tar.gz (6.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

akshare_mcp_server-0.1.1-py3-none-any.whl (7.3 kB view details)

Uploaded Python 3

File details

Details for the file akshare_mcp_server-0.1.1.tar.gz.

File metadata

  • Download URL: akshare_mcp_server-0.1.1.tar.gz
  • Upload date:
  • Size: 6.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.9

File hashes

Hashes for akshare_mcp_server-0.1.1.tar.gz
Algorithm Hash digest
SHA256 2f22830ce12a7f198b5b87d60865fc3a3f134fddd45a62580930708db6256672
MD5 a6d09584f28837cfe6fd4cfdeeeaf65f
BLAKE2b-256 e691755151310b0866036e553ceb9b6f42262765fe7bf2d06f4ff9c18393c7bb

See more details on using hashes here.

File details

Details for the file akshare_mcp_server-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for akshare_mcp_server-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 e42f30b58f65367bf5ab2992108a84eb783a85fa94d164630b0d25af4cb22266
MD5 a543c79b790f33f054ce02422a784ba8
BLAKE2b-256 bd91b0ef8e7e057524563e221bc2a58ff44eaf02256b5c17bdd02bfa0774ebd3

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page