aml-watcher-mcp-server
MCP Server for the AML Watcher API, enabling AML screening for individuals, companies, organizations, crypto wallets, vessels, and aircraft across various categories such as Sanctions, PEP Level 1, PEP Level 2, PEP Level 3, PEP Level 4, SIP, SIE, etc.
Documentation
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 how to add new arguments if needed.
Overview
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.
⚙️ Configuration
📝 Sign Up
🔑 How to Generate Your API Key
- Navigate to the **AML Watcher Developer Portal**.
- Click on “API Key” and copy it.
🖥️ Usage with Claude Desktop
Add this to your `claude_desktop_config.json`:
🐳 Docker
{
"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"
}
}
}
}- After this integration, the user has to provide a username.
🌐 Environment Arguments
Below is a detailed explanation of each environment argument specified in the `env` section of the `claude_desktop_config.json`. Each argument includes its purpose, type, default value, constraints, and instructions for setting or modifying its value.
| Argument | Type | Required | Default Value | Description |
|---|---|---|---|---|
| `API_KEY` | String | Yes | N/A | The API key for authentication. |
| `COUNTRIES` | Array | No | N/A | Array of countries to filter reports. Note: ISO 3166-1 alpha-2 country codes are supported. Example: `[\"CA\", \"IN\"]`. |
| `PER_PAGE` | Integer | No | 5 | The maximum number of results to return. |
| `MATCH_SCORE` | Integer | No | 80 | Match accuracy level (0–100). |
| `CATEGORIES` | Array | Yes | N/A | Filters reports by categories (e.g., `[\"SIP\", \"PEP Level 1\"]`). |
| `RCA_SEARCH` | Boolean | No | True | Whether to search within Relatives and Close Associates (RCA). |
| `ALIAS_SEARCH` | Boolean | No | True | Whether to search within aliases. |
You can define custom parameters inside the `env` section of your configuration file. These parameters are passed to the Docker container as environment variables.
🛠️ How to Add Environment Variables
Each variable listed in the `args` array using `-e` must have a matching key in the `env` section.
If a variable is not defined in the `env` block, the system may use a default value.
For example, if your `args` list contains:
"args": [
"-e", "PER_PAGE",
"-e", "MATCH_SCORE"
]Then your env should include:
"env": {
"PER_PAGE": "1",
"MATCH_SCORE": "80"
}💡Tip : If you want to manually set the value of a variable, make sure to use the exact same name as listed in the args section. Variable names must match exactly, otherwise the Docker container won't receive the value correctly.
Frequently asked questions
What is aml-watcher-mcp-server?
aml-watcher-mcp-server is MCP Server for the AML Watcher API, enabling AML screening for individuals, companies, organizations, crypto wallets, vessels, and aircraft across various categories such as Sanctions, PEP Level 1, PEP Level 2, PEP Level 3, PEP Level 4, SIP, SIE, etc.
How do I install aml-watcher-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is aml-watcher-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/Tech-AML/AML-watcher-MCP-Server.
Related MCP tools
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-gra...
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP