Aml Watcher MCP Server

This README provides detailed documentation for the AML Watcher MCP server configuration, focusing on the environment arguments used in the

Local serverstdio

What is the Aml Watcher MCP server?

Aml Watcher MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. This README provides detailed documentation for the AML Watcher MCP server configuration, focusing on the environment arguments used in the claude_desktop_config.json file. It explains each argument, how to set or modify its values, and.

What you get

The MCP server is configured to run a Docker container for AML (Anti-Money Laundering) screening. The configuration is defined in the claude_desktop_config.json file, which specifies the Docker command, arguments, and environment variables. The environment variables (env) control the behavior of the AML screening process, such as search parameters, filtering options, and monitoring settings.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Configuration and credentials

You will need 3 environment variables: API_KEY, PER_PAGE, MATCH_SCORE. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by tech-aml; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the aml watcher mcp server does with a few real requests.

How to install the Aml Watcher MCP server

{
  "mcpServers": {
    "aml": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e", "API_KEY",
        "-e", "PER_PAGE",
        "-e", "MATCH_SCORE",
        "-e", "CATEGORIES",
        "-e", "ALIAS_SEARCH",
        "-e", "RCA_SEARCH",
        "-e", "COUNTRIES",
        "techamlw/aml-watcher"
      ],
      "env": {
        "API_KEY": "api_key",
        "PER_PAGE": "1"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
API_KEYCredential the server authenticates with.Yes
PER_PAGEConfiguration value read at startup.Optional
MATCH_SCOREConfiguration value read at startup.Optional

Frequently asked questions

It connects Aml Watcher to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Aml Watcher directly.