Bond MCP Server

by pangahn

329 downloads Not rated yet MIT license
GitHub

About

# Bond MCP Server A lightweight, fast-deploy server for China bond market data integration, leveraging AkShare and MCP framework. ## Features - 📈 Integration with AkShare for financial data. - 🛠️ Easy setup with [uv](https://github.com/astral-sh/uv) for Python environment management. - ⚡ Simple configuration to use in…

Details

License
MIT license

Explore

- 📈 Integration with AkShare for financial data.
- 🛠️ Easy setup with uv for Python environment management.
- ⚡ Simple configuration to use in MCP client.

---

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Bond MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

- macOS / Linux system (or Windows with WSL)
- Homebrew installed (for macOS users)

Add the following configuration to your MCP client config file:

{
  "mcpServers": {
    "china-bond": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/bond-mcp-server",
        "run",
        "server.py"
      ],
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

> 🔔 Note: Replace /path/to/bond-mcp-server with the actual path where you cloned the project.

---

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "bond mcp server": {
            "bond-mcp-server": {
                "command": "uv",
                "args": [
                    "init",
                    "bond-mcp-server"
                ]
            }
        }
    }
}

McpServers

{
    "bond-mcp-server": {
        "command": "uv",
        "args": [
            "init",
            "bond-mcp-server"
        ]
    }
}

A lightweight, fast-deploy server for China bond market data integration, leveraging AkShare and MCP framework.

Features

- 📈 Integration with AkShare for financial data.
- 🛠️ Easy setup with uv for Python environment management.
- ⚡ Simple configuration to use in MCP client.

---

Development Setup

Prerequisites

- macOS / Linux system (or Windows with WSL)
- Homebrew installed (for macOS users)

Steps

1. Install uv package manager

brew install uv

2. Initialize project environment

uv init bond-mcp-server

3. Add project dependencies

uv add akshare "mcp[cli]"

---

Project Usage

1. Clone the repository

git clone [email protected]:pangahn/bond-mcp-server.git
cd bond-mcp-server

2. Sync dependencies

uv sync

This will install all required dependencies defined in the project.

---

3. Configure MCP Client

Add the following configuration to your MCP client config file:

{
  "mcpServers": {
    "china-bond": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/bond-mcp-server",
        "run",
        "server.py"
      ],
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

> 🔔 Note: Replace /path/to/bond-mcp-server with the actual path where you cloned the project.

---

4. Use in MCP Client

Once configured, simply start the MCP client. The china-bond server will automatically launch and be available for use within the client environment.

---

Additional Notes

- To update or add new packages:

uv add <package-name>
uv sync

- To remove a package:

uv remove <package-name>
uv sync

- Check available uv commands:

uv --help

---

License

MIT License

---

Would you like me to include example usage of how to query data from the server in the client as well?

No reviews yet — be the first

Sign in to leave a review

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

Email sign in

No reviews posted yet.