Ramp
Interact with Ramp's Developer API to run analysis on your spend and gain insights leveraging LLMs
ramp-mcp: A Ramp MCP server
Overview
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
Database tools
Tools that can be used to setup, process, query, and delete an ephemeral database in memory.
process_dataexecute_queryclear_table
Fetch tools
Tools that can be used to fetch data directly
get_ramp_categoriesget_currencies
Load tools
Loads 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.
Setup
Ramp Setup
- Create a new client from the Ramp developer page (Profile on top right > Developer > Create app)
- Grant the scopes you wish (based on tools) to the client and enable client credentials (Click on App > Grant Types / Scopes)
- Include the client ID and secret in the config file as well as the scopes you wish to use
Local Setup
- Clone this Github repo via
git clone [email protected]:ramp/ramp-mcp.gitor equivalent - Install
uv
Usage
Run 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>
Configuration
Usage with Claude Desktop
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/
License
Copyright (c) 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.
İlgili Sunucular
TempMail
Create temporary emails and read messages directly from your AI agent.
MCPApp
A Google Apps Script-based MCP network that allows AI to securely access Google Workspace data like Gmail and Calendar.
better-notion-mcp
Markdown-first Notion MCP server with 9 composite tools, 39 actions, and ~77% token reduction via tiered docs.
PyApple MCP Tools
Python tools for MCP that integrate with native Apple applications like Messages, Notes, Mail, and more on macOS.
Laravel Boost
Laravel Boost is an MCP server equipped with over 15 specialized tools designed to streamline AI-assisted coding workflows.
Enterpret
Enterpret's Wisdom MCP Server brings customer intelligence directly into your favorite AI tools.
MCP Hub
A manager server for MCP servers that handles process management and tool routing.
qa-use
Provides comprehensive browser automation for QA testing capabilities.
ComplianceCow MCP Server
Provides AI agents with compliance insights, auditable responses, and actions like ticket creation and policy fixes.
User Prompt MCP
An MCP server for Cursor that enables requesting user input during generation process.