How to integrate Nusii proposals MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
Nusii proposals Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Nusii proposals to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Nusii proposals agent that can create a new proposal for acme corp, send a follow-up email for pending proposal, list all proposals sent in the last month through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Nusii proposals account through Composio's Nusii proposals 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 and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Nusii proposals
  • Configure an AI agent that can use Nusii proposals as a tool
  • Run a live chat session where you can ask the agent to perform Nusii proposals operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Nusii proposals MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Nusii proposals account. It provides structured and secure access so your agent can perform Nusii proposals operations on your behalf.

Supported Tools & Triggers

Tools
Archive ProposalTool to archive a specific proposal in Nusii.
Create ClientTool to create a new client in Nusii Proposals.
Create Line ItemTool to create a line item within a proposal section.
Create ProposalTool to create a new proposal in Nusii.
Create SectionTool to create a section for a proposal or template in Nusii Proposals.
Create Webhook EndpointTool to create a webhook endpoint to subscribe to Nusii events.
Delete a clientTool to delete a specific client from Nusii account.
Delete Line ItemTool to delete a line item from Nusii.
Delete a proposalTool to delete a proposal from the system.
Delete a sectionTool to delete a specific section from Nusii.
Delete Webhook EndpointTool to delete a specific webhook endpoint from the system.
Get Account MeTool to retrieve authenticated user's personal account information and settings.
Get ClientTool to retrieve a single client from Nusii using their unique identifier.
Get ProposalTool to retrieve a single proposal with complete details and sections.
Get SectionTool to retrieve a single section from a proposal or template in Nusii.
Get Webhook EndpointTool to retrieve a single webhook endpoint configuration.
List ClientsTool to retrieve all clients associated with the account.
List Line ItemsTool to retrieve all line items from Nusii Proposals with pagination support.
List Proposal ActivitiesTool to retrieve all proposal activities with optional filtering by proposal or client ID.
List ProposalsTool to retrieve all proposals from your Nusii account with pagination and filtering options.
List Section Line ItemsTool to retrieve all line items from a specific section.
List SectionsTool to retrieve all sections with optional filtering for proposals or templates.
List ThemesTool to retrieve all available themes for proposals in Nusii.
List UsersTool to retrieve all users in paginated format.
List Webhook EndpointsTool to retrieve all webhook endpoints configured for your Nusii account.
Update ClientTool to update an existing client's information in Nusii.
Update Line ItemTool to update an existing line item in Nusii proposals.
Update ProposalTool to update an existing proposal in Nusii.
Update SectionTool to update an existing section in a proposal or template.

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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Nusii proposals project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Nusii proposals.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Nusii proposals Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["nusii_proposals"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only nusii_proposals.
  • The router checks the user's Nusii proposals connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Nusii proposals.
  • This approach keeps things lightweight and lets the agent request Nusii proposals tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Nusii proposals. "
        "Help users perform Nusii proposals operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Nusii proposals and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Nusii proposals operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Nusii proposals.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Nusii proposals and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["nusii_proposals"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Nusii proposals. "
        "Help users perform Nusii proposals operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Nusii proposals MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Nusii proposals.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Nusii proposals MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Nusii proposals MCP with Claude Agent SDK

Google ADK

Google ADK

Use Nusii proposals MCP with Google ADK

LangChain

LangChain

Use Nusii proposals MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Nusii proposals MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Nusii proposals MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Nusii proposals MCP with LlamaIndex

CrewAI

CrewAI

Use Nusii proposals MCP with CrewAI

Claude Code

Claude Code

Use Nusii proposals MCP with Claude Code

Codex

Codex

Use Nusii proposals MCP with Codex

FAQ

What are the differences in Tool Router MCP and Nusii proposals MCP?

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

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Nusii proposals tools.

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

Yes, absolutely. You can configure which Nusii proposals 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 Nusii proposals data and credentials are handled as safely as possible.

Used by agents from

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