
Ramp
CommunityPopularRamp MCP server. Access corporate card transactions, receipts, approval workflows, and expense reports. Automate finance ops from AI clients.
| Publisher | ramp-public |
| Repository | ramp-mcp-server |
| Language | TypeScript |
| Forks | 0 |
| Stars | 2.3K |
| Available tools | 16 |
| Transport type | stdio |
| Categories | |
| License | MIT |
| Links |
- Connect tools to AI workflows
Ramp exposes MCP capabilities that can be used by compatible AI clients and agents.
- 16 available tools
Browse the callable actions below, including names and descriptions when provided by the server.
- Ready-to-copy setup
Use the installation snippets to configure this server in your preferred MCP client.
- Open source signals
2.3K stars and 0 forks from the linked repository.
Installation
Node.js 18+
{
"mcpServers": {
"ramp": {
"command": "npx",
"args": [
"-y",
"ramp-mcp-server"
],
"env": {
"RAMP_CLIENT_ID": "<YOUR_CLIENT_ID>",
"RAMP_CLIENT_SECRET": "<YOUR_SECRET>"
}
}
}
}Available Tools
- list_transactions
Retrieve a paginated list of corporate card transactions with filtering options by date, amount, merchant, or card holder
- get_transaction
Get detailed information about a specific transaction including receipt data, categorization, and approval status
- search_transactions
Search transactions using flexible criteria like merchant name, amount ranges, categories, or custom metadata
- upload_receipt
Upload and attach receipt images or PDFs to existing transactions for expense documentation
- get_receipt
Retrieve receipt data and images associated with a specific transaction
- create_expense_report
Create a new expense report by grouping selected transactions and adding report metadata
- list_expense_reports
Get a list of expense reports with status information and filtering by date, employee, or approval state
- submit_expense_report
Submit an expense report for approval workflow processing
- approve_expense_report
Approve a pending expense report in the approval workflow
- reject_expense_report
Reject an expense report with comments and return it to the submitter
- get_approval_workflow
Retrieve the current approval workflow status and history for an expense report
- list_card_holders
Get a list of corporate card holders with their card details and spending limits
- update_transaction_category
Update the expense category and accounting codes for a transaction
- get_spending_analytics
Generate spending analytics and reports by department, category, time period, or card holder
- list_vendors
Retrieve a list of vendors and merchants with transaction history and spending totals
- export_expense_data
Export expense data in various formats (CSV, PDF, Excel) for accounting system integration
Use Ramp MCP with multiple AI models
TypingMind connects MCP tools at the workspace level, so once Ramp is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.
Setup guide to use the local connector
Use this when the MCP server needs access to local files, apps, or private resources on your computer.
Open the MCP settings
In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.
- Open TypingMind in your browser.
- Click the Settings icon.
- Go to Advanced Settings.
- Open the Model Context Protocol section.
- Click Setup Connector and choose This Device.

Run the connector command
Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.
- Copy the setup command shown by TypingMind.
- Open Terminal on macOS or Windows Terminal on Windows.
- Paste and run the command.
- Approve the package install if Terminal asks you to proceed.
- Keep the Terminal window running while using MCP tools.
Add Ramp as a server
When the connector status is Ready, click Edit Servers and paste the MCP server configuration.
- Wait until the connector status shows Ready.
- Click Edit Servers.
- Paste the Ramp MCP server configuration.
- Save the server list.
- Refresh if you want to confirm the connector is still ready.

{
"mcpServers": {
"ramp": {
"command": "npx",
"args": [
"-y",
"ramp-mcp-server"
]
}
}
}Use it across models
Save the server list, open Plugins, enable the Ramp MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.
- Open the Plugins page in TypingMind.
- Enable the Ramp MCP tools.
- Start a chat and choose the AI model you want to use.
- Use the MCP tools in chat or assign them to an AI agent.
- Switch to another AI model whenever needed without reconnecting MCP.


Here is what I found using Ramp.
Frequently asked questions
What is the Ramp MCP server used for?
Ramp is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.
Can I use Ramp MCP with multiple AI models in TypingMind?
Yes. TypingMind connects MCP tools at the workspace level, so you can use Ramp with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.
Why use Ramp MCP with TypingMind?
TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Ramp connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.
How do I connect Ramp MCP to TypingMind?
Ramp runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.
What tools does Ramp MCP provide in TypingMind?
Ramp exposes 16 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.
Do I need to share my API keys with TypingMind to use Ramp MCP?
No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Ramp requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.
Related MCP Servers
View all
PayPal
Official PayPal MCP server. Process payments, manage subscriptions, handle disputes, and access transaction history via PayPal's REST APIs.
TradingView MCP Server
Real-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick patterns + native Claude Desktop integration. Multi-exchange (Binance, KuCoin, Bybit+). Open-source AI trading infrastructure.
Financial Datasets
An MCP server for interacting with the Financial Datasets stock market API.
Solana Agent Kit
connect any ai agents to solana protocols
