finance_ops · finance · workflow
Ramp builds MCP server enabling natural language querying of business spend data via Claude
Ramp's initial MCP prototype ran into scaling issues—miscalculations, limited context windows, input size limits, and high token usage—preventing it from handling more than a few hundred transactions when connecting Claude to business spend data.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Natural language query submitted
A user submits a natural language query about business spend via Claude Desktop as the MCP client.
Tools used
FastMCPClaude DesktopSQLiteClaude
Outcome
After switching to a SQL-based paradigm with in-memory SQLite, Claude went from struggling with a few hundred data points to accurately analyzing tens of thousands of spend events.
What failed first
A simple pagination tool built to chunk API responses into smaller parts did not solve the scaling problem.
Results
Cost replacedfrom struggling with a few hundred data points to accurately analyzing tens of thousands of spend events
Grounding & classification
Source type: technical build writeup
20 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowdata extractionenterprise searchsummarizationbuilder submittedfailure mode describedmetric backednamed customertools describedfinancial servicessoftwarethroughput increasetechnical build writeupback office opsfinance opsagentic task execution