How to integrate Simplekpi MCP with OpenAI Agents SDK

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

Introduction

This guide walks you through connecting Simplekpi to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Simplekpi agent that can show me top performing kpis this month, add a new kpi for sales pipeline, generate a report on marketing metrics through natural language commands.

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

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

Supported Tools & Triggers

Tools
Add User Group ItemTool to assign a group item to a user in SimpleKPI.
Add User KPITool to assign a KPI to a user in SimpleKPI.
Create Category KPITool to create a new KPI within a category in SimpleKPI.
Create GroupTool to create a new group in SimpleKPI.
Create Group ItemTool to create a new item within a group in SimpleKPI.
Create KPITool to create a new KPI with specified configuration.
Create KPI CategoryTool to create a new KPI category in SimpleKPI.
Create KPI UnitTool to create a new KPI unit in SimpleKPI.
Batch KPI EntriesTool to batch create or update multiple KPI entries at once.
Create UserTool to create a new user account in SimpleKPI.
Delete Category KPITool to delete a KPI from a category.
Delete GroupTool to delete a group by ID.
Delete Group ItemTool to delete a group item by ID.
Delete KPITool to delete a KPI by ID.
Delete KPI CategoryTool to delete a KPI category by its ID.
Delete KPI EntryTool to delete a KPI entry by ID.
Delete KPI UnitTool to delete a KPI unit by its ID.
Delete UserTool to delete a user account by ID.
Delete User Group ItemTool to remove a group item assignment from a user.
Delete User KPITool to remove a KPI assignment from a user.
Get All Data EntriesTool to retrieve processed KPI data entries for reports including calculated KPIs.
Get Category KPITool to retrieve a specific KPI within a category.
Get GroupTool to get a specific group by ID from SimplekPI.
Get Group ItemTool to retrieve a specific group item by ID.
Get KPI by IDTool to retrieve a specific KPI by ID from SimpleKPI.
Get KPI CategoryTool to get a specific KPI category by ID from SimpleKPI.
Get KPI EntryTool to retrieve a specific KPI entry by ID.
Get KPI FrequencyTool to get a specific KPI frequency by ID from SimplekPI.
Get KPI Icon by IDTool to retrieve a specific KPI icon by ID.
Get KPI UnitTool to get a specific KPI unit by ID from SimpleKPI.
Get User by IDTool to retrieve a specific user by ID.
Get User Group ItemTool to get a specific group item assigned to a user.
Get User KPITool to retrieve a specific KPI assigned to a user.
List Category KPIsTool to retrieve all KPIs within a specific category.
List Group ItemsTool to get all items within a group.
List GroupsTool to retrieve all groups from SimpleKPI.
List KPI CategoriesTool to get all KPI categories.
List KPI EntriesTool to get all KPI entries filtered by date range and optional criteria.
List KPI FrequenciesTool to get all KPI frequencies.
List KPI IconsTool to retrieve all KPI icons from SimpleKPI.
List All KPIsTool to retrieve all KPIs from a SimpleKPI account.
List All KPI UnitsTool to retrieve all KPI units from a SimpleKPI account.
List User Group ItemsTool to get all group items assigned to a user.
List User KPIsTool to get all KPIs assigned to a specific user.
Update Category KPITool to update a KPI within a category.
Update GroupTool to update an existing group in SimpleKPI.
Update Group ItemTool to update an existing item in a SimpleKPI group.
Update KPITool to update an existing KPI in SimpleKPI.
Update KPI EntryTool to update an existing KPI entry in SimpleKPI.
Update KPI UnitTool to update an existing KPI unit in SimpleKPI.
Update UserTool to update an existing user account in SimpleKPI.

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 Simplekpi 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 Simplekpi.

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 Simplekpi Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["simplekpi"]
)

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

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 Simplekpi MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Simplekpi MCP with Claude Agent SDK

Google ADK

Google ADK

Use Simplekpi MCP with Google ADK

LangChain

LangChain

Use Simplekpi MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Simplekpi MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Simplekpi MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Simplekpi MCP with LlamaIndex

CrewAI

CrewAI

Use Simplekpi MCP with CrewAI

Claude Code

Claude Code

Use Simplekpi MCP with Claude Code

Codex

Codex

Use Simplekpi MCP with Codex

FAQ

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

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

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

Yes, absolutely. You can configure which Simplekpi 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 Simplekpi 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