A Model Context Protocol server for retrieving and analyzing data or running tasks for Ramp using Developer API. In order to get around token and input size limitations, this server implements a simple ETL pipeline + ephemeral sqlite database in memory for analysis by an LLM. All requests are made to demo by default, but can be changed by setting RAMP_ENV=prd. Large datasets may not be processable due to API and/or your MCP client limitations.
Tools that can be used to setup, process, query, and delete an ephemeral database in memory.
process_dataexecute_queryclear_tableTools that can be used to fetch data directly
get_ramp_categoriesget_currenciesLoads data to server which the client can fetch. Based on the tools you wish to use, ensure to enable those scopes on your Ramp client and include the scopes when starting the server as a CLI argument.
| Tool | 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 |
For large datasets, it is recommended to explicitly prompt Claude not to use REPL and to keep responses concise to avoid timeout or excessive token usage.
git clone [email protected]:ramp/ramp-mcp.git or equivalentuvRun the MCP server from your CLI with:
RAMP_CLIENT_ID=... RAMP_CLIENT_SECRET=... RAMP_ENV=<demo|prd> uv run ramp-mcp -s <COMMA-SEPARATED-SCOPES>
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"ramp-mcp": {
"command": "uv",
"args": [
"--directory",
"/<ABSOLUTE-PATH-TO>/ramp-mcp", // make sure to update this path
"run",
"ramp-mcp",
"-s",
"transactions:read,reimbursements:read"
],
"env": {
"RAMP_CLIENT_ID": "<CLIENT_ID>",
"RAMP_CLIENT_SECRET": "<CLIENT_SECRET>",
"RAMP_ENV": "<demo|qa|prd>"
}
}
}
}
If this file doesn’t exist yet, create one in /<ABSOLUTE-PATH-TO>/Library/Application Support/Claude/
Copyright © 2025, Ramp Business Corporation All rights reserved. This source code is licensed under the MIT License found in the LICENSE file in the root directory of this source tree.
Code Explainer Mcp
A Cloudflare Worker that serves as an MCP (Model Context Protocol) server for code explanation. It analyzes and explains code with a comprehensive breakdown of structure and functionality.
Raindrop Io Mcp Server
Mcp Name Origin Server
A Python-based MCP (Model Context Protocol) server that predicts the origin
A Model Context Protocol (MCP) server that provides real-time cryptocurrency analysis via CoinCap's API. Enables Claude and other MCP clients to fetch crypto prices, analyze market trends, and track historical data.
Model Context Protocol server for OpenStreetMap data
Get Python Docs
Model Context Protocol server for Audius. Perform market research, purchase premium tracks, upload songs, and much more!