process_dataLABSCO SUMMARY
Spend analysis as SQL, not as pagination.
The reason a finance question is painful over an API is that the answer spans more rows than a conversation can hold. Loading the dataset into an in-memory database first makes the question a query — and the database goes away with the session.
What it is
A Ramp Developer API client with an ETL step in front of it. Rather than returning API pages into the conversation, the load tools pull a dataset into an ephemeral in-memory SQLite database, which you then query with SQL — that is how it gets around token and input size limits.
What you get
- Transactions, reimbursements and bills loaded for analysis
- Vendors and vendor bank accounts, users, departments, locations, entities and bank accounts
- Spend limits and spend programs
- Ramp categories and currencies fetched directly, for when a lookup is all you need
- An ephemeral in-memory database: data processed into it, queried with SQL, and tables cleared when you are done
Requirements
uv, and a Ramp client with client credentials enabled — its id and secret go in the client entry's environment as RAMP_CLIENT_ID and RAMP_CLIENT_SECRET. Each load tool needs its own read scope granted on the client; the scopes go on the launch command after -s. Requests go to the demo environment unless you set RAMP_ENV to prd. Large datasets may not be processable within API and client limits.
Setup effort
Build from source — git clone https://github.com/ramp-public/ramp_mcp
USE CASES
01
Asking where the money went last quarter
Load the transactions, process them into the ephemeral database, and answer with a query rather than by reading pages.
02
Breaking spend down by team or place
Load departments, locations and entities alongside the transactions and join across them.
03
Reviewing what you pay vendors
Bring vendors and bills in together and look at the relationship, not one invoice at a time.
04
Checking reimbursements before they are approved
Load them and query for the ones that need a second look.
05
Auditing spend controls
Load the spend limits, the spend programs and the users they apply to, and see where policy and practice differ.
06
Keeping a long session workable
Clear a table once you are finished with it, and pull categories, currencies or bank accounts directly when a lookup is enough.
17 tools
Listed in project docs. Your client may show a different list.
execute_queryclear_tableget_ramp_categoriesget_currenciesload_transactionsload_reimbursementsload_billsload_locationsload_departmentsload_bank_accountsload_vendorsload_vendor_bank_accountsload_entitiesload_spend_limitsload_spend_programsload_usersBEFORE YOU INSTALL
What to know first
Tools you get
17 tools named in the project's documentation.
Requires
- uv on PATH
- RAMP_CLIENT_ID in your environment
- RAMP_CLIENT_SECRET in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/ramp-public/ramp_mcpInstall uv
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"ramp-mcp": {
"command": "uv",
"args": [
"--directory",
"/<YOUR_ABSOLUTE_PATH_TO>/ramp-mcp",
"run",
"ramp-mcp",
"-s",
"transactions:read,reimbursements:read"
],
"env": {
"RAMP_CLIENT_ID": "<YOUR_RAMP_CLIENT_ID>",
"RAMP_CLIENT_SECRET": "<YOUR_RAMP_CLIENT_SECRET>",
"RAMP_ENV": "<YOUR_RAMP_ENV>"
}
}
}
}
