How to integrate Plain MCP with OpenAI Agents SDK

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

Introduction

This guide walks you through connecting Plain to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Plain agent that can add a customer to the enterprise group, fetch company details for acme corp, list all issues linked to this customer, create a new support thread for user through natural language commands.

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

The Plain MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Plain account. It provides structured and secure access to your B2B support workspace, so your agent can perform actions like managing customers, creating support threads, fetching company details, handling issues, and organizing customer groups on your behalf.

  • Customer management and onboarding: Automatically create new customer records, fetch customer information by email or ID, and add customers to specific support groups for better organization.
  • Support thread creation: Let your agent create new support threads tied to customers, making it easy to kick off or escalate conversations without manual intervention.
  • Issue tracking and retrieval: Fetch all external issue links associated with a customer, helping your team stay on top of ongoing problems and resolutions.
  • Company and tier information access: Retrieve detailed company profiles and tier metadata, including contract value, owner details, and more, to personalize support interactions.
  • User and customer cleanup: Safely delete customers or users from the system when offboarding or data hygiene is needed, all through agent-driven actions.

Supported Tools & Triggers

Tools
Add Customer To GroupTool to add a customer to one or more customer groups.
Create CustomerTool to create a customer.
Create ThreadTool to create a new thread.
Delete CustomerTool to delete a customer from the system.
Delete UserTool to delete a user from the system.
Fetch CompanyTool to fetch company details by id.
Fetch IssuesTool to fetch external issue links for a customer.
Fetch TierTool to fetch a tier by its id.
Get Customer By EmailTool to fetch customer details by email.
Get Customer By IDTool to retrieve details of a specific customer by their unique id.
Get CustomersTool to fetch a list of customers.
Get Thread By IDTool to fetch details of a specific thread using its unique identifier.
Get User By IDTool to fetch user by id.
List ThreadsTool to list all threads.
List TiersTool to retrieve a list of tiers with pagination.
Create Customer GroupTool to create a new customer group.
List Customer GroupsTool to list all customer groups.
List ThreadsTool to retrieve a paginated list of threads.
Remove Customer From GroupTool to remove a customer from one or more customer groups.
Send MessageTool to send a new message within a thread.
Update CompanyTool to update an existing company's details.
Update ThreadTool to update a thread's title.
Upsert CustomerTool to upsert (create or update) a customer.

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 Plain 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 Plain.

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 Plain Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["plain"]
)

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

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 Plain MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Plain MCP with Claude Agent SDK

Google ADK

Google ADK

Use Plain MCP with Google ADK

LangChain

LangChain

Use Plain MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Plain MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Plain MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Plain MCP with LlamaIndex

CrewAI

CrewAI

Use Plain MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Plain 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 Plain 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 callā†—Get started for free