How to integrate Inistate MCP with Autogen

This guide walks you through connecting Inistate to AutoGen using the Composio tool router. By the end, you'll have a working Inistate agent that can create entries, update your records, change workflow states, review entry history, and list workspaces through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Inistate account through Composio's Inistate MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Inistate logoInistate
Api Key

Inistate is a workspace platform for building workflow and record-management applications. It helps teams configure modules, track entries, audit changes, and manage files in one place.

12 Tools

Introduction

This guide walks you through connecting Inistate to AutoGen using the Composio tool router. By the end, you'll have a working Inistate agent that can create entries, update your records, change workflow states, review entry history, and list workspaces through natural language commands.

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

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

Also integrate Inistate with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Inistate
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Inistate tools
  • Run a live chat loop where you ask the agent to perform Inistate operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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

The Inistate MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Inistate account. It provides structured and secure access to your workspaces, modules, records, activities, and audit history, so your agent can inspect application structures, find records, create or update entries, manage workflow states, and review changes on your behalf.

  • Workspace and module discovery: Have your agent find accessible workspaces, list their modules, and review each module's fields, states, activities, and flows.
  • Record search and review: Let the agent find records using saved listings, filters, search terms, sorting, and selected fields, then inspect their values, state, audit details, and available activities.
  • Record creation and updates: Direct your agent to check required activity fields and available options before creating new records or updating existing ones.
  • Workflow state management: Instruct your agent to request state changes for one record or up to 100 records in the same module, while accounting for low confidence results.
  • Bulk changes and audit review: Have your agent update fields across up to 100 records in one module and review a record's comments, field changes, audit trail, and AI traceability context.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Inistate account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Inistate via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Inistate connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Inistate session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["inistate"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Inistate tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Inistate assistant agent with MCP tools
    agent = AssistantAgent(
        name="inistate_assistant",
        description="An AI assistant that helps with Inistate operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Inistate tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Inistate related question or task to the agent.\n")

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

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

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Inistate tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Inistate and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

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

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Inistate assistant agent with MCP tools
        agent = AssistantAgent(
            name="inistate_assistant",
            description="An AI assistant that helps with Inistate operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Inistate related question or task to the agent.\n")

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

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

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Inistate through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Inistate, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Inistate action and event your agent gets out of the box.

Bulk Change Entry States

Request state transitions for 1-100 entries in one module.

Bulk Update Entries

Update fields on 1-100 entries in one module.

Change Entry State

Request a state transition for one module record; low confidence can flag the result and suppress the transition.

Create Entry

Create one record in a module through its create activity and return whether low confidence caused it to be flagged.

Get Activity Form

Get the required fields, current values, options, defaults, and confidence threshold for a module activity before submitting it.

Get Entry

Get one module record by ID, including its current values, state, audit metadata, and available activities.

Get Entry History

Return one chronological 50-item page of a record's audit trail, comments, field changes, and AI traceability context.

Get Module Schema

Get a module's fields and states, optionally including its activities and flows, before querying or changing records.

List Entries

Return one page of records from a module using a saved listing, field filters, search, sorting, and field projection.

List Modules

List modules available in a workspace so their exact names can be used in schema and record tools.

List Workspaces

List workspaces accessible to the connected API key, optionally filtering by workspace name.

Update Entry

Update fields on one existing module record through its edit activity and return whether low confidence caused it to be flagged.

FRAMEWORKS

How to build Inistate MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Inistate MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Inistate MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Inistate MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Inistate MCP with Claude Cowork

Codex logo

Codex

Use Inistate MCP with Codex

OpenClaw logo

OpenClaw

Use Inistate MCP with OpenClaw

Hermes logo

Hermes

Use Inistate MCP with Hermes

CLI logo

CLI

Use Inistate MCP with CLI

Google ADK logo

Google ADK

Use Inistate MCP with Google ADK

LangChain logo

LangChain

Use Inistate MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Inistate MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Inistate MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Inistate MCP with LlamaIndex

CrewAI logo

CrewAI

Use Inistate MCP with CrewAI

FAQ

Frequently asked questions

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

Yes, you can. Autogen 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 Inistate tools.

Yes, absolutely. You can configure which Inistate 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.

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 Inistate data and credentials are handled as safely as possible.

Start with Inistate.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Inistate tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies