Cloud · MODEL CONTEXT PROTOCOL
Shioaji-MCP
MCP server for SinoPac shioaji api
WHAT IT CONNECTS
What Shioaji-MCP gives an AI Agent
The source catalog does not include a structured feature list. Review the repository documentation before use.
SECURITY
An MCP listing is not a security review
An MCP server may receive model context, credentials, local files, or permission to call external systems. Review its code, requested environment variables, network behavior, package provenance, and maintenance status before connecting it to an agent.
README
Repository documentation
An end-to-end example of building Model Context Protocol (MCP) clients and communicates between several MCP servers with OpenAI compatible APIs.
You can run your MCP servers with a similar method as you run them with Claude Desktop App for just a simple command:
uv run python client/client.py- Make sure you have
uvinstalled.
uv venv
source .venv/bin/activate
uv sync- Shioaji: An example MCP server that provides basic stock trading functionalities using Shioaji API, you'll need further configuration to properly use it.
- Weather: Just a simple example from MCP official doc
Instead of following the Claude API, I replace it with OpenAI compatible APIs, supporting two main LLM providers:
- OpenAI
- Ollama
Where you can change between them by modifying the LLM_PROVIDER environment variable.
After choosing your LLM provider, you can connect servers with the MCP host by modifying the config.json file, just like the example below:
{
"mcpServers": {
"weather": {
"args": [
"--directory",
"root_path",
"run",
"server_file.py"
],
"command": "uv_exec_command"
}
}
}You can run the MCP host with the following command:
uv run python client/client.pyAfter finishing playing with the MCP host, you can just type exit to leave
The shioaji-server in
server/is certified by MCP Review. The mcp review link
COMMUNITY