How to integrate Ramp MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Ramp Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Ramp to CrewAI using the Composio tool router. By the end, you'll have a working Ramp agent that can download last month's statement as pdf, list all transactions over $500 this week, get details of my virtual cards, create a new department for marketing through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Ramp account through Composio's Ramp MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Ramp connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Ramp
  • Build a conversational loop where your agent can execute Ramp operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

What is the Ramp MCP server, and what's possible with it?

The Ramp MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ramp account. It provides structured and secure access to your company's financial data, so your agent can fetch transactions, analyze card activity, generate statements, manage departments, and retrieve detailed expense information on your behalf.

  • Comprehensive transaction tracking: Instantly pull lists of all your business transactions or your own card activity, making it easy to monitor expenses and spot anomalies.
  • Card management and insights: Retrieve details about specific Ramp cards or see all cards assigned to you, including limits, status, and cardholder info for better financial oversight.
  • Automated statement generation: Ask your agent to generate and download account statements in multiple formats (PDF, CSV, JSON) for reporting or bookkeeping.
  • Department and organizational management: Create new departments or fetch detailed department profiles to help structure your expense tracking and categorize spending.
  • Detailed transaction analysis: Dive into specific transactions to get merchant information, receipts, dispute details, and accounting codes for audit and compliance purposes.

Supported Tools & Triggers

Tools
Create DepartmentTool for creating a new department in your ramp organization.
Create New Custom Accounting FieldTool for creating a new custom accounting field.
Fetch Custom Accounting FieldTool for fetching a custom accounting field.
Get All TransactionsGet all the transactions.
Get CardTool for retrieving detailed information about a specific card.
Get DepartmentTool for retrieving detailed information about a specific department.
Get My CardsTool for fetching cards assigned to you, including physical and virtual cards.
Get My TransactionsGet my transactions.
Get StatementTool for retrieving statement details or downloading statements.
Get Transaction DetailsTool for retrieving complete details of a specific transaction.
Get Vendor DetailsTool for retrieving detailed information about a specific vendor.
Issue Virtual CardTool for issuing virtual cards to users instantly.
List All CardsTool for listing all cards across the organization with optional filters.
List DepartmentsTool for listing all departments in the organization.
List StatementsTool for listing all statements with filtering options.
List UsersTool for listing users in your ramp organization with flexible filtering.
List VendorsTool for listing vendors with their spending information.
Options for Custom Accounting FieldTool for listing options for a given accounting field.
Search TransactionsSearch transactions with filters.
Update Card Spending LimitTool for updating spending limits on a card.
Update DepartmentTool for updating an existing department in your ramp organization.
Upload New Options for Custom Accounting FieldTool for uploading new options for a given accounting field.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Ramp connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Ramp via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Ramp MCP URL

Create a Composio Tool Router session for Ramp

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["ramp"],
)
url = session.mcp.url
What's happening:
  • You create a Ramp only session through Composio
  • Composio returns an MCP HTTP URL that exposes Ramp tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Ramp Assistant",
    goal="Help users interact with Ramp through natural language commands",
    backstory=(
        "You are an expert assistant with access to Ramp tools. "
        "You can perform various Ramp operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Ramp MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Ramp operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Ramp related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_ramp_agent.py

Complete Code

Here's the complete code to get you started with Ramp and CrewAI:

python
# file: crewai_ramp_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Ramp session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["ramp"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Ramp assistant agent
    toolkit_agent = Agent(
        role="Ramp Assistant",
        goal="Help users interact with Ramp through natural language commands",
        backstory=(
            "You are an expert assistant with access to Ramp tools. "
            "You can perform various Ramp operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Ramp operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Ramp related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Ramp through Composio's Tool Router. The agent can perform Ramp operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Ramp MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Ramp MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Ramp MCP with Claude Agent SDK

Google ADK

Google ADK

Use Ramp MCP with Google ADK

LangChain

LangChain

Use Ramp MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Ramp MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Ramp MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Ramp MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Ramp MCP?

With a standalone Ramp MCP server, the agents and LLMs can only access a fixed set of Ramp tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ramp and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Ramp tools.

Can I manage the permissions and scopes for Ramp while using Tool Router?

Yes, absolutely. You can configure which Ramp scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Ramp data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free