Skip to main content
Automate expense workflows with Expensify MCP to export reports, reconcile corporate card transactions, and create expenses in bulk using natural language prompts. Quickly feed structured data into your downstream automations and keep finance teams in sync.
Export reports and card transactions to CSV, Excel, PDF, or XML, then receive a public download link that seamlessly feeds the next step in your workflow.

​
How to Use MCP Nodes

​
Authentication

To use the node, you will need to generate API credentials.

​
What is Expensify MCP?

Expensify MCP creates an AI-generated node that understands the Expensify API. Provide a focused, single-action prompt, and the AI returns structured data for reports, card transactions, or bulk expense creation, making it easy to integrate Expensify into any Gumloop workflow.

​
What Can It Do for You?

  • Export expense reports for a custom date range and receive a downloadable link in your preferred file format
  • Reconcile corporate card transactions by exporting transaction files for any period
  • Create expenses in bulk with categories, tags, and custom fields to keep ledgers current
  • Pass structured outputs directly into Google Sheets, BI tools, or other automations

​
Available Tools

ToolWhat It DoesExample Use
Get ReportsExport Expensify reports in CSV, Excel, PDF, or XML and return a public download URL”Export reports from start date to end date in file format and return structured data with the public download_url”
Get Card TransactionsExport card transactions for reconciliation in multiple formats and return a public download URL”Export corporate card transactions for start date to end date in file format and return structured data with the public download_url”
Create ExpensesCreate expenses in bulk in a user’s account with support for categories, tags, and custom fields”Using structured data list expenses list for user email that includes merchant, amount, currency, date, category, tags, and custom fields, create expenses and return structured data confirming creation”

​
How to Use

1

Create Your Expensify MCP Node

Go to your node library, search for Expensify, and click “Create a node with AI”
2

Add Your Prompt

Drag the Expensify MCP node to your canvas and add your prompt in the text box.
3

Test Your Node

Run the node to see the results. If it works as expected, you’re all set! If you run into issues, check the troubleshooting tips below.
4

Save and Reuse

Once your Expensify MCP node is working, save it to your library. You can now use this customized node in any workflow.

​
Example Prompts

Here are some prompts that work well with Expensify MCP: Report Exports: 
Export expense reports from `start date` to `end date` in `file format` and return structured data with the public `download_url`
Filtered Report Exports: 
Export reports from `start date` to `end date` with state `report state` in `file format` and return structured data with the public `download_url`
Card Transaction Reconciliation: 
Export corporate card transactions for `start date` to `end date` in `file format` and return structured data with the public `download_url`
Bulk Expense Creation: 
Using structured data list `expenses list` for `user email` that includes `merchant`, `amount`, `currency`, `date`, `category`, `tags`, and `custom fields`, create expenses and return structured data confirming creation
Start with clear variables like start date, end date, and file format. Focus each prompt on a single action for fast, reliable results.

​
Troubleshooting

If your Expensify MCP node isn’t working as expected, try these best practices:

​
Keep Prompts Simple and Specific

  • Good: “Export reports from start date to end date in file format and return the public download_url”
  • Bad: “Export reports, summarize totals by category, update a Google Sheet, and email finance”
While the second prompt might seem convenient, it can lead to timeouts or unexpected behavior. For best results, create separate nodes for exporting, summarizing, and emailing.

​
Match What Expensify Can Do

  • Good: “Create expenses for user email from expenses list and return structured data confirming creation”
  • Bad: “Create expenses and then post journal entries to my accounting system”
Expensify MCP excels at expense reporting and transaction data retrieval. For accounting system updates, connect the output to the relevant node within your workflow like the Call API or Google Sheets Writer nodes.

​
Break Complex Tasks Into Steps

Attempting everything at once might slow down processing: 
Export all reports for `month`, export corporate card transactions for `month`, create expenses from `new expenses list`, and email approvers with `message template`
A more efficient approach is to break this into focused prompts:
1

Step 1: Export Reports

Export reports from start date to end date in file format and return structured data with the public download_url
2

Step 2: Export Card Transactions

Export corporate card transactions from start date to end date in file format and return structured data with the public download_url
3

Step 3: Create Expenses

Using structured data list expenses list for user email, create expenses with categories, tags, and custom fields and return structured data confirming creation
Connect these nodes sequentially in your workflow. The download link from Step 1 can feed into Extract Data or Ask AI, while the expenses list for Step 3 comes from your prior processing step.

​
Focus on Data Retrieval

Expensify MCP is great at getting information from Expensify. For summaries or insights, link it to other nodes. Example:
  • Good prompt: “Export corporate card transactions for start date to end date and return the public download_url”
  • Bad prompt: “Export card transactions and summarize top merchants by spend”
Use Ask AI for summaries and insights, or Extract Data to parse structured data from files after you download them.

​
Troubleshooting Node Creation

If you’re seeing empty outputs in the node creation window (or if you’ve already created the node, hover over it and click “Edit”), use the chat interface to prompt the AI to add debug logs and verify the API response. Specifically mention that you received empty outputs.
In the node creation window (or if you’ve already created the node, hover over it and click “Edit”), use the chat interface to describe in detail what you expected versus what you received.
First click “Fix with Gummie”. If multiple attempts fail, simplify your prompt or contact support.
MCP node creation often requires a few tweaks. Use the chat interface in the node creation window to refine filters, output fields, or pagination. The AI will adjust the node based on your feedback.

​
Need More Help?

⌘I