ACA PoC MCP Tools Server
Enables AI agents to generate audit reports and query financial ledger data via MCP. This demo version contains intentional security vulnerabilities for security testing and should not be used in production.
README
ACA PoC MCP Tools Server (Vulnerable Demo Version)
⚠️ WARNING: This repository contains intentional security vulnerabilities for demonstration purposes only. DO NOT use in production!
Financial audit and ledger query tools exposed via Model Context Protocol (MCP) - Vulnerable Version for Security Testing.
Overview
This MCP server provides AI agents with tools to:
- Generate Audit Reports: Create compliance, risk, and transaction summary reports
- Query Financial Ledger: Access transaction data, balances, and summaries from an in-memory SQLite database
⚠️ Known Vulnerabilities (Intentional)
This version contains the following security vulnerabilities for demonstration:
- SQL Injection - Unsafe query construction in ledger queries
- Command Injection - Unsafe shell command execution in report generation
- Path Traversal - Unsafe file path handling in export functionality
- Hardcoded Secrets - API keys and passwords in source code
- Insecure Deserialization - Unsafe pickle usage
- XXE (XML External Entity) - Unsafe XML parsing
- SSRF (Server-Side Request Forgery) - Unsafe URL fetching
- Weak Cryptography - MD5 hashing for sensitive data
- Insecure Dependencies - Outdated vulnerable packages
- Information Disclosure - Verbose error messages with stack traces
Tools
1. generate_audit_report
Generate comprehensive audit reports for financial data.
Parameters:
report_type: Type of report (compliance,risk,transaction)date_range(optional): Date range filter withstart_dateandend_dateformat(optional): Output format (jsonorcsv)export_path(optional): File path for export (⚠️ vulnerable to path traversal)
2. query_ledger
Query financial ledger data from the in-memory database.
Parameters:
query_type: Type of query (transactions,balance,summary)filter(optional): SQL filter clause (⚠️ vulnerable to SQL injection)limit(optional): Maximum number of results (default: 100)
Installation
Using Docker
docker build -t aca-mcp-tools-vulnerable .
docker run -p 8080:8080 aca-mcp-tools-vulnerable
Local Development
# Install dependencies
pip install -r requirements.txt
# Run the server
python main.py
MCP Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"aca-financial-tools-vulnerable": {
"url": "http://localhost:8080",
"transport": "streamable-http"
}
}
}
Security & Compliance
- Status: ⚠️ VULNERABLE - For demonstration only
- Phase: 0 (Not production-ready)
- Owner: ACA PoC Team
License
MIT License - See LICENSE file for details
Disclaimer
This software is provided for educational and demonstration purposes only. It contains intentional security vulnerabilities and should never be deployed in production environments or used with real data.
Contact
ACA PoC Team - aca-poc@dell.com
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.