This MCP server enables you to retrieve and analyze data from Ramp using the Developer API. It implements an ETL pipeline with an ephemeral SQLite database in memory for LLM analysis, helping to overcome token and input size limitations.
git clone [email protected]:ramp/ramp-mcp.git
uv
:
Start the MCP server from your command line:
RAMP_CLIENT_ID=... RAMP_CLIENT_SECRET=... RAMP_ENV=<demo|prd> uv run ramp-mcp -s <COMMA-SEPARATED-SCOPES>
Replace the placeholder values with your actual Ramp credentials. By default, requests are made to the demo environment, but you can set RAMP_ENV=prd
for production.
To use this MCP server with Claude Desktop:
claude_desktop_config.json
file in /<ABSOLUTE-PATH-TO>/Library/Application Support/Claude/
{
"mcpServers": {
"ramp-mcp": {
"command": "uv",
"args": [
"--directory",
"/<ABSOLUTE-PATH-TO>/ramp-mcp",
"run",
"ramp-mcp",
"-s",
"transactions:read,reimbursements:read"
],
"env": {
"RAMP_CLIENT_ID": "<CLIENT_ID>",
"RAMP_CLIENT_SECRET": "<CLIENT_SECRET>",
"RAMP_ENV": "<demo|qa|prd>"
}
}
}
}
Be sure to update the directory path and include your actual credentials.
These tools help you manage the ephemeral in-memory database:
process_data
: Set up and process dataexecute_query
: Run SQL queries against the databaseclear_table
: Delete data from the databaseDirect data retrieval tools:
get_ramp_categories
: Retrieve Ramp categoriesget_currencies
: Get currency informationTools that load data to the server for client retrieval. Enable the corresponding scopes for the tools you want to use:
Tool | Required Scope |
---|---|
load_transactions |
transactions:read |
load_reimbursements |
reimbursements:read |
load_bills |
bills:read |
load_locations |
locations:read |
load_departments |
departments:read |
load_bank_accounts |
bank_accounts:read |
load_vendors |
vendors:read |
load_vendor_bank_accounts |
vendors:read |
load_entities |
entities:read |
load_spend_limits |
limits:read |
load_spend_programs |
spend_programs:read |
load_users |
users:read |
Note: For large datasets, it's recommended to prompt Claude not to use REPL and to keep responses concise to avoid timeout or excessive token usage.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.