Ramp Mcp: A Ramp Mcp Server

What is ramp_mcp?

The ### ramp_mcp is a public repository hosted on GitHub under the organization ### ramp-public. This repository is designed to facilitate various functionalities related to the management and processing of data, particularly in the context of ramping up computational processes. It serves as a collaborative platform for developers and contributors to enhance and maintain the codebase.

Features of ramp_mcp

• Open Source: The repository is publicly accessible, allowing anyone to view, use, and contribute to the code.
• Collaboration: It supports multiple contributors, enabling collaborative development and improvement of the project.
• Version Control: Utilizing Git, ramp_mcp maintains a history of changes, making it easy to track modifications and revert to previous versions if necessary.
• Documentation: Comprehensive documentation is provided to assist users in understanding the functionalities and usage of the repository.
• License: The project is licensed under the MIT license, promoting freedom to use, modify, and distribute the software.

How to Use ramp_mcp

1. Clone the Repository: Start by cloning the repository to your local machine using the command:

   git clone https://github.com/ramp-public/ramp_mcp.git
   

2. Install Dependencies: Navigate to the cloned directory and install any necessary dependencies as outlined in the documentation.

3. Explore the Code: Familiarize yourself with the structure and functionality of the codebase. Documentation files are typically included to guide you through the various components.

4. Contribute: If you wish to contribute, create a new branch, make your changes, and submit a pull request for review.

5. Stay Updated: Keep track of updates by watching the repository on GitHub, which will notify you of any changes or new releases.

Frequently Asked Questions

What programming languages are used in ramp_mcp?

The ramp_mcp repository primarily utilizes languages such as Python and JavaScript, among others, depending on the specific functionalities being implemented.

How can I report issues or bugs?

You can report issues by navigating to the "Issues" tab in the repository and submitting a new issue with a detailed description of the problem.

Is there a community for ramp_mcp?

Yes, the community can be engaged through GitHub discussions, issues, and pull requests. Additionally, you can find discussions on platforms like Slack or Discord if they are set up by the maintainers.

Can I use ramp_mcp in my own projects?

Absolutely! Since it is open-source and licensed under the MIT license, you are free to use, modify, and distribute the code as per the terms of the license.

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.

1. process_data
2. execute_query
3. clear_table

Fetch tools

Tools that can be used to fetch data directly

1. get_ramp_categories
2. get_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

1. Create a new client from the Ramp developer page (Profile on top right > Developer > Create app)
2. Grant the scopes you wish (based on tools) to the client and enable client credentials (Click on App > Grant Types / Scopes)
3. Include the client ID and secret in the config file as well as the scopes you wish to use

Local Setup

1. Clone this Github repo via git clone git@github.com:ramp/ramp-mcp.git or equivalent
2. 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.