How to integrate Agiled MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Agiled Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Agiled to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Agiled agent that can create a new project for client onboarding, list all active deals for this month, add a business expense from yesterday, fetch employee directory with job titles through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Agiled account through Composio's Agiled 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 Agiled
  • Configure an AI agent that can use Agiled as a tool
  • Run a live chat session where you can ask the agent to perform Agiled 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 Agiled MCP server, and what's possible with it?

The Agiled MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Agiled account. It provides structured and secure access to your CRM, project management, finance, and support tools, so your agent can perform actions like creating tasks, managing expenses, retrieving contacts, and handling support tickets on your behalf.

  • Project and task automation: Instantly create new projects or tasks, assign them to team members, set due dates, and update project boards—all through your agent.
  • Expense and estimate management: Let your agent create new expense records, fetch all expenses, or retrieve estimates for up-to-date financial tracking without manual data entry.
  • CRM and contact retrieval: Effortlessly pull up all your contacts or deals, making it easy for your agent to surface leads, customers, or CRM reports when you need them.
  • Support ticket creation: Enable your agent to open new support tickets, capture customer issues, and track priority items directly in Agiled.
  • Employee directory access: Quickly fetch employee lists for team coordination, assignment, or HR workflows, ensuring your agent always has current organizational info.

Supported Tools & Triggers

Tools
Create ExpenseTool to create a new expense in agiled.
Create ProjectTool to create a new project in agiled.
Create TaskTool to create a new task in agiled.
Create TicketTool to create a new support ticket in agiled.
Get ContactsTool to retrieve a list of all contacts.
Get CurrenciesTool to list currencies.
Get DealsTool to retrieve a list of all deals.
Get EmployeesTool to retrieve a list of all employees.
Get EstimatesTool to retrieve a list of all estimates.
Get ExpensesTool to retrieve a list of all expenses.
Get InvoicesTool to retrieve a list of all invoices from agiled.
Get ProductsTool to retrieve a list of all products.
Get Project CategoriesTool to retrieve a list of all project categories.
Get ProjectsTool to retrieve a list of all projects.
GET_TASKSTool to retrieve a list of all tasks.
Get TicketsTool to retrieve a list of all tickets.
Get TimesheetsTool to retrieve timesheets for a project.
Get UsersTool to retrieve a list of users from agiled.

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 Agiled 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 Agiled.

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 Agiled Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["agiled"]
)

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 agiled.
  • The router checks the user's Agiled connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Agiled.
  • This approach keeps things lightweight and lets the agent request Agiled 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 Agiled. "
        "Help users perform Agiled 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 Agiled 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 Agiled 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 Agiled.
  • 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 Agiled 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=["agiled"]
)
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 Agiled. "
        "Help users perform Agiled 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 Agiled MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Agiled.

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 Agiled MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Agiled MCP with Claude Agent SDK

Google ADK

Google ADK

Use Agiled MCP with Google ADK

LangChain

LangChain

Use Agiled MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Agiled MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Agiled MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Agiled MCP with LlamaIndex

CrewAI

CrewAI

Use Agiled MCP with CrewAI

FAQ

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

With a standalone Agiled MCP server, the agents and LLMs can only access a fixed set of Agiled tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Agiled 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 Agiled tools.

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

Yes, absolutely. You can configure which Agiled 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 Agiled 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