- Home
- MCP servers
- MCPIOL
MCPIOL
- python
2
GitHub Stars
python
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"fernandezpablo85-mcpiol": {
"command": "/Users/YOUR_USERNAME/.local/bin/uv",
"args": [
"--directory",
"/Users/YOUR_USERNAME/projects/playground/mcpiol",
"run",
"main.py"
],
"env": {
"IOL_PASS": "YOUR_PASSWORD",
"IOL_USER": "YOUR_USERNAME"
}
}
}
}You can use this MCP server to interact with the IOL API through Claude Desktop by running a local MCP instance that executes a Python script via uv. This setup lets you manage IOL operations from Claude Desktop with a dedicated, self-contained environment.
How to use
To use the MCP server, you run the local MVP process via Claude Desktop and point it to the project directory where your MCP script lives. The server executes the main workflow and connects Claude Desktop to the IOL API using your credentials stored in environment variables. You can manage your IOL trades and related actions through the MCP interface by starting the local server via the configured command and directory.
How to install
Prerequisites you need to prepare before starting the MCP server:
-
Claude Desktop App for Mac
-
Python 3.8+
-
IOL trading account
-
Environment variables set with your IOL credentials (IOL_USER and IOL_PASS)
Step-by-step commands to configure and run the MCP server locally:
# 1) Install uv (if not already installed)
# Use the installation script from the project environment
curl -LsSf https://astral.sh/uv/install.sh | sh
# 2) Ensure uv is available in your PATH
which uv
# 3) Create a project directory for your MCP work
mkdir -p /Users/YOUR_USERNAME/projects/playground/mcpiol
# 4) Install dependencies for the project (if you use uv to sync dependencies)
uv sync
# 5) Create environment file with your IOL credentials
# In your project root, create a .env file with credentials
cat > .env << 'ENV'
IOL_USER=your_username
IOL_PASS=your_password
ENV
# 6) Place your MCP script (e.g., main.py) in the project directory as needed
# Ensure the script is ready to run for the MCP workflow
# 7) Configure Claude Desktop to run the MCP via uv (see next section)
Configuration for Claude Desktop
Open the Claude Desktop configuration directory to set up the MCP server integration. You will point Claude Desktop to run uv with your MCP script from a specific directory.
Place the MCP configuration JSON inside the Claude Desktop config path, using an absolute path for both the command and the working directory.
{
"mcpServers": {
"iol": {
"command": "/Users/YOUR_USERNAME/.local/bin/uv",
"args": [
"--directory",
"/Users/YOUR_USERNAME/projects/playground/mcpiol",
"run",
"main.py"
]
}
}
}
Additional notes on configuration and credentials
Important notes to finalize configuration and ensure secure access to the IOL API:
-
Replace YOUR_USERNAME with your actual username in all paths.
-
Both the command path and the --directory path must be absolute.
-
You can determine your uv installation path by running
which uvin the terminal.
Troubleshooting
If you encounter issues, try the following steps to verify and correct setup:
-
Ensure the configuration JSON is correctly formatted and uses absolute paths.
-
Restart Claude Desktop after making changes to the configuration.
-
Confirm your IOL credentials are correctly defined in the .env file and that the file exists.
-
Check that your IOL API status is operational and that your IOL account is active.
Security and usage notes
-
Keep your IOL credentials secure and do not expose them in public or shared systems.
-
Use environment variables to manage sensitive information and avoid hard-coding credentials in scripts.
License and contribution
MIT license applies for the MCP server setup and tools.