MBBank

MCP server for MBBank API enabling monitoring and analytics of transactions and balances.
  • python

8

GitHub Stars

python

Language

6 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": {
    "thedtvn-mbbank-mcp": {
      "command": "uvx",
      "args": [
        "mbbank-mcp",
        "--username=<your_username>",
        "--password=<your_password>"
      ],
      "env": {
        "MBBANK_PASSWORD": "<your_password>",
        "MBBANK_USERNAME": "<your_username>"
      }
    }
  }
}

This MCP Server enables monitoring and analytics for MBBank API by collecting transactions and balances data. It is designed to run locally or in container environments, and it supports both direct runtime execution and containerized deployments so you can integrate it with your existing monitoring workflows.

How to use

You can run the MBBank MCP Server locally using the runtime command or inside a Docker container. In both cases, you provide your MBBank credentials to enable data collection. For security, avoid exposing credentials in shared environments and prefer environment variables when using containers.

Starting with a local runtime, you can enable secure streaming output by using the standard input/output (stdio) mode or switch to server-sent events (SSE) mode for real-time data pushes. The runtime supports optional host and port configuration so you can expose the MCP server on your desired network address.

If you choose Docker, you run the MCP server as a container and pass credentials via environment variables. The container image is designed to read MBBANK_USERNAME and MBBANK_PASSWORD from the environment, matching the examples shown in the container configuration.

How to install

Prerequisites you need before installation: the uv runtime and Python 3.10 or higher. Ensure Python is installed on your system and that you have network access to install or run the MCP components.

Option A: Install and run via CLI runtime (stdio mode) using uvx. Create or prepare a configuration that includes your credentials. Replace the placeholders with your actual username and password.

{
  "mcpServers": {
    "mbbank": {
      "command": "uvx",
      "args": [
        "mbbank-mcp",
        "--username=<your_username>",
        "--password=<your_password>"
      ]
    }
  }
}

Option B: Run via Docker. Use container environment variables to provide credentials and map them into the container. This approach keeps credentials out of your local command history.

{
  "mcpServers": {
    "mbbank": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MBBANK_USERNAME",
        "-e",
        "MBBANK_PASSWORD",
        "thedtvn/mbbank-mcp:latest"
      ],
      "env": {
        "MBBANK_USERNAME": "<your_username>",
        "MBBANK_PASSWORD": "<your_password>"
      }
    }
  }
}

Additional notes

To run in standalone mode with SSE enabled, add the --sse flag. If you prefer standard I/O mode, omit --sse. You can also provide credentials via command-line flags or environment variables MBBANK_USERNAME and MBBANK_PASSWORD.

Default host and port for the standalone server are localhost:3000. You can customize them with --host and --port when starting the server.

Security and usage notes

This MCP server reads sensitive data such as account balances and transactions. Use it only with trusted applications and environments. Do not expose credentials in shared or unencrypted channels, and consider scope-limiting permissions for any service accounts involved.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
MBBank MCP Server - thedtvn/mbbank-mcp | VeilStrat