Finance ops · Production

Ramp builds an MCP server enabling natural-language analysis of business spend data with Claude

The problem

Ramp's business data was accessible only through API calls, with no way to query or understand spend using natural language without writing code.

First attempt

The initial MCP prototype ran into scaling issues—miscalculations, limited context windows, input size limits, and high token usage—and could not reliably handle more than a few hundred transactions.

Workflow diagram · grounded in source

Natural language query trigger

trigger

“We asked Claude to "give me a detailed overview of my business's spend in the past year."”

Pull data from Ramp API

integration

“load_transactions) to pull data from the Ramp API”

ETL into in-memory SQLite

integration

“process_data tool to transform the data from the API and load into the SQLite table”

Claude executes SQL queries

ai_action

“execute_query to run queries on the in-memory database directly”

Generate analysis and visualizations

output

“Claude was able to both generate visualizations and run simple analyses on spend data pulled from Ramp's APIs using natural language”

Reported outcome

After switching to a SQL-based paradigm with an in-memory SQLite database, Claude could accurately analyze tens of thousands of spend events, and the solution even worked with the free version of Claude due to reduced token usage.

Reported metrics

Data analysis scale improvementfrom struggling with a few hundred data points to accurately analyzing tens of thousands of spend events

Initial results qualitymind-blowing

Reported stack

Ramp MCPFastMCPClaude DesktopClaudeSQLiteRamp developer APIModel Context ProtocolOLAP

Source

https://builders.ramp.com/post/ramp-mcp

Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

After switching to a SQL-based paradigm with an in-memory SQLite database, Claude could accurately analyze tens of thousands of spend events, and the solution even worked with the free version of Claude due to reduced…

What tools did this team use?

Ramp MCP, FastMCP, Claude Desktop, Claude, SQLite, Ramp developer API, Model Context Protocol, OLAP.

What results were reported?

Data analysis scale improvement: from struggling with a few hundred data points to accurately analyzing tens of thousands of spend events; Initial results quality: mind-blowing (source-reported, not independently verified).

What failed first in this deployment?

How is this finance ops AI workflow structured?

Natural language query trigger → Pull data from Ramp API → ETL into in-memory SQLite → Claude executes SQL queries → Generate analysis and visualizations.