AbnerTeng/end2end-mcp
If you are the rightful owner of end2end-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP (Model Context Protocol) server for Shioaji API.
end2end-mcp
An end-to-end example of building Model Context Protocol (MCP) clients and communicates between several MCP servers with OpenAI compatible APIs.
TL;DR
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
Prerequisites
- Make sure you have
uvinstalled.
uv venv
source .venv/bin/activate
uv sync
Brief Introduction
Example MCP servers
- 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
MCP host
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.
Connect with MCP host
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"
}
}
}
Run MCP host
You can run the MCP host with the following command:
uv run python client/client.py
After 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
