FraudLabs Pro

Created By
fraudlabspro8 hours ago
FraudLabs Pro MCP server is a Model Context Protocol (MCP) server that provides order or user transaction validations using the FraudLabs Pro API. This server allows AI agents to validate an order or user transaction, get the validation result for an order or user transaction, and update the status for an order or user transaction.
Overview

The FraudLabs Pro MCP Server is a powerful integration designed to bring high-performance fraud prevention intelligence directly into your LLM-driven workflows. By utilizing the Model Context Protocol (MCP), this server allows your AI agents to validate an order or user transaction, get the validation result for an order or user transaction, and update the status for an order or user transaction using a single natural language prompt.

Key Features

  • Order Screening: Validate e-commerce orders using IP addresses, billing/shipping details, and credit card information.

  • User Screening: Analyze account-level events (registrations/logins) for suspicious patterns.

  • Transaction Management: Retrieve historical results for orders or user screenings.

  • Feedback Loop: Approve, Reject, or Blacklist transactions directly through the AI interface to improve the detection engine.

Prerequisites

  • Python 3.10+ installed.
  • FraudLabs Pro API Key: You can obtain a free or paid API key at FraudLabs Pro.

Installation

  1. Install Dependencies Ensure you have the required libraries installed in your environment:
pip install mcp httpx
  1. Configuration To use this server with an MCP client (such as Claude Desktop), add the following entry to your configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "fraudlabspro": {
      "command": "python3",
      "args": ["/absolute/path/to/fraudlabspro/src/server.py"],
      "env": {
        "FRAUDLABSPRO_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Available Tools

📦 Order Management

ToolDescriptionKey Arguments
screen_orderScreen an order for fraud.ip, email, amount, bin_no, bill_country, ship_country
get_order_resultRetrieve the validation result for a previous order.transaction_id
feedback_orderUpdate order status (APPROVE, REJECT, BLACKLIST).transaction_id, action, note

👤 User Management

ToolDescriptionKey Arguments
screen_userScreen user events like logins or signups.email, ip, phone, first_name, last_name
get_user_resultRetrieve results for a previous user screening.user_transaction_id
feedback_userUpdate user event status based on manual review.user_transaction_id, action, reason

Development & Logging

The server uses FastMCP and sends logs through the MCP context. You can view logs in the Claude Desktop "Developer Console" to inspect outgoing payloads and API responses for debugging.

Common Error: If you receive "An API key is needed," ensure the FRAUDLABSPRO_API_KEY environment variable is correctly set in your configuration file and that you have restarted the MCP client.

License

See the LICENSE file.

Server Config

{
  "mcpServers": {
    "fraudlabspro": {
      "command": "python3",
      "args": [
        "/absolute/path/to/fraudlabpro/src/server.py"
      ],
      "env": {
        "FRAUDLABSPRO_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
Project Info
Created At
8 hours ago
Updated At
8 hours ago
Author Name
fraudlabspro
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

18 hours ago
奇门遁甲

20 hours ago