akshare_mcp

by wukan1986

15 stars

248 downloads

Not rated

GitHub

Other

About

aksharemcp is an MCP (Model Context Protocol) server wrapper that exposes all data interfaces from the AKShare financial data library as tools for MCP clients. It is built for users who need access to AKShare's full dataset without manually limiting to a small subset.

Details

Author: wukan1986
GitHub stars: 15
Downloads: 248
Categories: Other

- Exposes all 1,000+ AKShare data interfaces as MCP tools
- Supports custom selection of interfaces via configuration files
- Outputs data in markdown format for readability
- Allows external configuration file path via --config parameter
- Compatible with any MCP client that supports tool invocation

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name akshare_mcp

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

From the repository

Install via pip install akshare_mcp or uv pip install akshare_mcp, then run python -m akshare_mcp -h to verify installation and note the configuration file path. In your MCP client’s JSON configuration, set the command to your Python interpreter and args to ["-m", "akshare_mcp", "--format", "markdown"]. To avoid excessive token usage, edit the config.py file (found via -h) to list only the interfaces you need, or use --config <path> to point to a custom config file. After editing, reconnect the MCP client.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "akshare_mcp": {
            "akshare_mcp": {
                "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
                "args": [
                    "-m",
                    "akshare_mcp",
                    "--format",
                    "markdown"
                ]
            }
        }
    }
}

McpServers

{
    "akshare_mcp": {
        "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
        "args": [
            "-m",
            "akshare_mcp",
            "--format",
            "markdown"
        ]
    }
}

akshare_mcp

AKShare数据接口的MCP Server封装

项目背景

AKShare提供了上千个数据接口，但Github上提供的服务都只支持少量接口，所以本项目将所有接口都暴露出来，方便用户使用。

安装

1. 在虚拟环境下执行pip install akshare_mcp或uv pip install akshare_mcp，
2. 运行python -m akshare_mcp -h检查是否安装成功，留意打印的配置文件路径

配置

{
  "mcpServers": {
    "akshare_mcp": {
      "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
      "args": [
        "-m",
        "akshare_mcp",
        "--format",
        "markdown"
      ]
    }
  }
}

注意

1. 1000+接口，全部暴露成工具，将会消耗大量Token
2. 部分MCP客户端只支持少量的工具，例如Trae最多支持40个工具

所以，请一定在使用前配置需要使用的接口。

1. 运行python -m akshare_mcp -h，查看配置文件的位置。例如d:\Users\Kan\miniconda3\envs\py312\Lib\site-packages\akshare_mcp\config.py
2. 编辑配置文件config.py，添加需要使用的接口。接口名参考https://akshare.akfamily.xyz/data/index.html
3. MCP客户端刷新重连服务端

如果site-packages\akshare_mcp\config.py无权限修改，可以从github上复制config.py文件到任意路径，然后使用--config参数

python -m akshare_mcp --config D:\config.py

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

akshare_mcp

项目背景

安装

配置

注意

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀