beginner⏱️ 14-24 minutes📅 Updated June 2026

Step-by-step guide to integrate Adfin MCP server with NVIDIA Agent Intelligence Toolkit. Includes credit control management and invoice creation and management.

Adfin + NVIDIA Agent Intelligence Toolkit: Complete MCP Integration

Adfin is a MCP server that The only platform you need to get paid - all payments in one place, invoicing and accounting reconciliations with Adfin..

When integrated with NVIDIA Agent Intelligence Toolkit, you can:

  • Monitor and manage customer credit status and payment tracking
  • Create individual invoices with customizable details
  • Upload and process multiple PDF invoices simultaneously

This guide provides step-by-step instructions to set up Adfin in NVIDIA Agent Intelligence Toolkit, including configuration, examples, and troubleshooting.

What You'll Achieve

After completing this setup:

  • Adfin will be fully integrated and operational
  • You can use Adfin tools directly in NVIDIA Agent Intelligence Toolkit
  • All Adfin capabilities will be available for your workflows
  • Access to 5 different tools

Prerequisites

Before starting, ensure you have:

  • Adfin account email address
  • Adfin account password
  • NVIDIA Agent Intelligence Toolkit installed and configured
  • Compatible operating system (Python Package (pip), Docker Container, Framework Integration)

Installation

Step 1: Install Adfin

Configuration

Step 2: Configure NVIDIA Agent Intelligence Toolkit

  1. Open NVIDIA Agent Intelligence Toolkit settings
  2. Navigate to MCP server configuration
  3. Add Adfin server with appropriate settings
  4. Save and restart if needed

Examples

Once configured, you can use Adfin in NVIDIA Agent Intelligence Toolkit:

Credit Control Status Check

Review overall credit control status for all customers

Ask NVIDIA Agent Intelligence Toolkit: "Give me a credit control status check for all our customers"

Expected Result: Comprehensive report showing customer payment status, overdue amounts, and credit risks

Create New Invoice

Generate an invoice for a specific customer with custom terms

Ask NVIDIA Agent Intelligence Toolkit: "Create a new invoice for 60 GBP for Abc Def that is due in a week"

Expected Result: Invoice created with customer details, amount, and 7-day payment terms

Bulk Invoice Upload

Process multiple PDF invoices from a directory

Ask NVIDIA Agent Intelligence Toolkit: "Upload all pdf invoices from the invoices folder from my Desktop"

Expected Result: All PDF invoices processed, validated, and uploaded to Adfin system

Payment Reconciliation

Match received payments with outstanding invoices

Ask NVIDIA Agent Intelligence Toolkit: "Reconcile the payment of £1,250 received today with our outstanding invoices"

Expected Result: Payment matched to appropriate invoices with reconciliation details recorded

Testing Your Setup

  1. Launch NVIDIA Agent Intelligence Toolkit
  2. Verify Adfin is available in the tools list
  3. Test basic Adfin functionality

Troubleshooting

Common Issues

Authentication Failed

Symptoms: Login errors, Invalid credentials messages, 401 Unauthorized

Cause: Incorrect ADFIN_EMAIL or ADFIN_PASSWORD

Solution:

  • Verify email and password are correct in Adfin web interface
  • Check for typos in environment variables
  • Ensure credentials are not expired or locked
  • Reset password if necessary through Adfin portal

UV Package Manager Not Found

Symptoms: Command not found errors, uv command fails

Cause: UV package manager not installed or not in PATH

Solution:

  • Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
  • Restart terminal to update PATH
  • Verify installation: uv --version
  • For Windows: use PowerShell installation script

PDF Invoice Processing Fails

Symptoms: Upload errors, PDF parsing failures, Invalid file format

Cause: Corrupted PDFs, unsupported format, or file permissions

Solution:

  • Verify PDFs are valid and readable
  • Check file permissions allow read access
  • Ensure PDFs contain text (not just images)
  • Try uploading files individually to isolate issues

Claude Desktop Configuration Error

Symptoms: MCP server not detected, Configuration syntax errors

Cause: Invalid JSON syntax or incorrect configuration structure

Solution:

  • Validate JSON syntax in claude_desktop_config.json
  • Ensure proper nesting of mcpServers configuration
  • Check file is in correct location for Claude Desktop
  • Restart Claude Desktop after configuration changes

MCP Server Connection Failed

Symptoms: Connection refused errors, Timeout connecting to MCP server, URL not responding

Cause: MCP server not running or incorrect URL configuration

Solution:

  • Verify MCP server is running and accessible
  • Check URL in configuration matches server endpoint
  • Ensure network/firewall allows connection to server port
  • Test connection with curl or browser before agent integration

Tool Schema Validation Errors

Symptoms: Invalid input format errors, Schema mismatch warnings, Type validation failures

Cause: Input data does not match MCP tool schema

Solution:

  • Use CLI to inspect tool schema: aiq info mcp --url <url> --tool <name>
  • Validate input data matches expected types and required fields
  • Check JSON schema definitions in MCP server documentation
  • Convert inputs to proper format (dict, JSON string, or schema instance)

Framework Integration Issues

Symptoms: Import errors, Framework not found, Incompatible versions

Cause: Missing or incompatible framework dependencies

Solution:

  • Ensure target framework (LangChain, LlamaIndex, etc.) is installed
  • Check version compatibility between AIQ toolkit and framework
  • Install framework-specific dependencies as needed
  • Refer to documentation for framework-specific configuration

Performance Bottlenecks

Symptoms: Slow agent responses, High token usage, Workflow timeouts

Cause: Inefficient tool usage or workflow design

Solution:

  • Enable observability to identify bottlenecks
  • Use profiling features to analyze tool and agent performance
  • Review token tracking metrics to optimize LLM calls
  • Consider hyperparameter tuning for agent optimization

OpenTelemetry Integration Errors

Symptoms: Observability data not appearing, Telemetry export failures, Missing metrics

Cause: OpenTelemetry not properly configured

Solution:

  • Verify OpenTelemetry collector is running
  • Check observability configuration in AIQ settings
  • Ensure proper instrumentation of agent workflows
  • Review OpenTelemetry export settings and endpoints

Adfin not appearing in NVIDIA Agent Intelligence Toolkit

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

  • Verify configuration syntax
  • Check Adfin installation
  • Restart NVIDIA Agent Intelligence Toolkit
  • Check logs for error messages

Next Steps

Now that Adfin is integrated with NVIDIA Agent Intelligence Toolkit:

  • Explore all Adfin capabilities through NVIDIA Agent Intelligence Toolkit
  • Check out other MCP servers that work with NVIDIA Agent Intelligence Toolkit
  • Join the MCP community for tips and support
  • Consider contributing to Adfin development

Need Help?

Related Resources

More Integrations

Explore other MCP servers that work with NVIDIA Agent Intelligence Toolkit

Need Help?

Join the MCP community for support and discussions

Adfin + NVIDIA Agent Intelligence Toolkit: MCP Setup Guide (2026)