fintual_mcp_server

This MCP server connects your LLM to Fintual's API via a Python-based server. It exposes a set of tools for interacting with asset providers, conceptual assets, and banks within Fintual, enabling you to query provider details, asset concepts, and bank integrations through the MCP interface. To use it, start the UV runner with the specified command and point it at the server.py file for the fintual_python_server. Once the server is running, you can invoke the MCP tools in your prompts, such as assets_provider, conceptual_assets, and banks, to retrieve structured data from Fintual's API. The workflow typically involves prompting the model to decide whether to call a tool, performing the API-backed query, and then receiving the results to craft a final answer for the user.

Prerequisites:

• Python environment (for the Python server) and access to UV (the MCP runner).
• Access to the fintual_python_server directory with server.py.

Installation steps:

1. Clone the repository:

git clone https://github.com/davila7/fintual_mcp_server.git

2. Install UV (if not already installed):

curl -LsSf https://astral.sh/uv/install.sh | sh

3. Navigate to the Python server directory:

cd fintual_mcp_server/fintual_python_server

4. Run the MCP server via UV (example placeholders shown; replace paths accordingly):

uv run --with mcp[cli] mcp run <path_to_your_repo>/fintual_mcp_server/fintual_python_server/server.py

5. Verify the server is running and accessible according to your environment and the UV output.

Notes and tips:

• Replace the placeholder path /path_to_your_uv/.local/bin/uv with the actual path to your uv executable.
• Replace <path to mcp-servers>/fintual_mcp_server/fintual_python_server/server.py with the actual filesystem path to server.py.
• The API docs for Fintual are available at https://fintual.cl/api-docs/index.html for reference when crafting prompts that use the tools.
• If you encounter connectivity or authentication issues with Fintual's API, ensure any required API keys or OAuth flows are configured in your environment as needed by the Python server.
• This server currently emphasizes Python-based tooling; TypeScript support is listed as coming soon.