How to integrate Baselinker MCP with Autogen

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Baselinker logo
AutoGen logo
divider

Introduction

This guide walks you through connecting Baselinker to AutoGen using the Composio tool router. By the end, you'll have a working Baselinker agent that can list all orders from this week, find orders placed by john@example.com, show pending receipts waiting to be issued through natural language commands.

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

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

Also integrate Baselinker with

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 Baselinker
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Baselinker tools
  • Run a live chat loop where you ask the agent to perform Baselinker 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 Baselinker MCP server, and what's possible with it?

The Baselinker MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Baselinker account. It provides structured and secure access to your e-commerce data, so your agent can perform tasks like managing orders, tracking inventory, processing receipts, and retrieving sales information on your behalf.

  • Order management and retrieval: Let your agent fetch, filter, and download order details—including by date, status, or customer email—for fast access to sales and customer data.
  • Inventory and purchase order tracking: Automatically retrieve current inventory documents, view purchase orders, and get document series to keep your stock and supply chain in check.
  • External storage and warehouse discovery: Seamlessly list all external stores and warehouses connected to your Baselinker account, so your agent knows where your products live.
  • Order status and custom field mapping: Ask your agent to pull order statuses or extra field definitions, making it easy to interpret, categorize, and automate order processing flows.
  • Pending receipt management: Quickly fetch receipts that still need to be issued, helping your team stay on top of fiscal compliance and transaction documentation.

Supported Tools & Triggers

Tools
Add InventoryTool to add or update a BaseLinker catalog (inventory).
Add Inventory CategoryTool to add or update a category in the BaseLinker catalog.
Add Inventory DocumentTool to create a new inventory document in BaseLinker storage.
Add Inventory ManufacturerTool to add or update a manufacturer in the BaseLinker catalog.
Add Inventory PayerTool to add a new payer or update an existing one in BaseLinker storage.
Add Inventory Price GroupTool to create or update a price group in BaseLinker storage.
Add Inventory ProductAdd a new product to BaseLinker catalog or update an existing product.
Add Inventory Purchase OrderTool to create a new purchase order in BaseLinker storage.
Add Inventory Purchase Order ItemsTool to add items to an existing purchase order in BaseLinker.
Add Inventory SupplierTool to add a new supplier or update an existing one in BaseLinker storage.
Add Inventory WarehouseTool to add a new warehouse or update an existing warehouse in BaseLinker inventories.
Add InvoiceTool to issue an order invoice in BaseLinker.
Add Invoice CorrectionTool to issue an order invoice correction.
Add OrderTool to add a new order to the BaseLinker order manager.
Add Order By SplitTool to create a new order by splitting selected products from an existing order.
Add Order DuplicateTool to add a new order by duplicating an existing order in BaseLinker.
Add Order ReturnTool to add a new order return to BaseLinker.
Add Order Return ProductTool to add a new product to an existing order return in BaseLinker.
Add Shop CategoryTool to add a new category to BaseLinker storage (shops, warehouses, or BaseLinker inventory).
Create Package ManualTool to register shipping details for orders when shipments are created outside BaseLinker.
Delete InventoryTool to delete a catalog from BaseLinker storage.
Delete Inventory CategoryTool to remove categories from BaseLinker warehouse.
Delete Inventory ManufacturerTool to remove a manufacturer from the BaseLinker catalog.
Delete Inventory PayerTool to remove a payer from BaseLinker storage.
Delete Inventory Price GroupTool to remove a price group from BaseLinker storage.
Delete Inventory ProductTool to remove a product from the BaseLinker catalog.
Delete Inventory WarehouseTool to remove a warehouse from BaseLinker inventories.
Delete Order ProductTool to remove a specific product from an order in BaseLinker.
Delete Order Return ProductTool to remove a specific product from an order return in BaseLinker.
Delete OrdersTool to delete multiple orders from BaseLinker order manager.
Get Connect Integration ContractorsTool to retrieve a list of contractors connected to a selected Base Connect integration.
Get Connect IntegrationsTool to retrieve a list of all Base Connect integrations on this account.
Get Courier AccountsTool to retrieve the list of accounts connected to a given courier.
Get Courier FieldsTool to retrieve the form fields required for creating shipments with a specific courier.
Get Courier Packages Status HistoryTool to retrieve the history of status changes for courier packages.
Get Couriers ListTool to retrieve a list of available couriers from BaseLinker.
Get External Storage Products QuantityRetrieve stock quantities from an external storage (shop/wholesaler) connected to BaseLinker.
Get External Storages ListRetrieve a list of external storages (shops, warehouses, wholesalers) connected to BaseLinker that can be referenced via API.
Get InventoriesTool to retrieve a list of catalogs (inventories) available in the BaseLinker storage.
Get Inventory Available Text Field KeysTool to retrieve a list of product text fields that can be overwritten for a specific integration.
Get Inventory CategoriesTool to retrieve a list of categories for a BaseLinker catalog.
Get Inventory Document ItemsTool to retrieve items from inventory documents in BaseLinker.
Get Inventory DocumentsTool to retrieve a list of inventory documents.
Get Inventory Document SeriesTool to retrieve available inventory document series.
Get Inventory Extra FieldsTool to retrieve extra fields defined for BaseLinker catalog inventory items.
Get Inventory IntegrationsTool to retrieve a list of integrations where text values in the catalog can be overwritten.
Get Inventory ManufacturersTool to retrieve a list of manufacturers from the BaseLinker catalog.
Get Inventory PayersTool to retrieve a list of payers available in BaseLinker storage.
Get Inventory Price GroupsTool to retrieve price groups existing in BaseLinker storage.
Get Inventory Printout TemplatesTool to retrieve a list of all configured printout templates available for inventory (products).
Get Inventory Product LogsTool to retrieve a list of events related to product changes in the BaseLinker catalog.
Get Inventory Products DataTool to retrieve detailed data for selected products from the BaseLinker inventory.
Get Inventory Products ListTool to retrieve basic data of chosen products from BaseLinker catalogs.
Get Inventory Products PricesRetrieve gross prices of products from BaseLinker inventories.
Get Inventory Products StockTool to retrieve stock data of products from BaseLinker catalogs.
Get Inventory Purchase Order ItemsTool to retrieve items from a specific purchase order in BaseLinker.
Get Inventory Purchase OrdersTool to retrieve a list of purchase orders from BaseLinker storage.
Get Inventory Purchase Order SeriesTool to retrieve a list of purchase order document series.
Get Inventory SuppliersTool to retrieve a list of suppliers available in BaseLinker storage.
Get Inventory TagsTool to retrieve a list of tags for a BaseLinker catalog.
Get Inventory WarehousesTool to retrieve a list of warehouses available in BaseLinker inventories.
Get Invoice FileTool to retrieve an invoice file from BaseLinker in base64-encoded format.
Get InvoicesDownload invoices from BaseLinker order manager with optional filtering.
Get Journal ListTool to download order event logs from the last 3 days.
Get New ReceiptsTool to retrieve receipts waiting to be issued.
Get Order Extra FieldsTool to retrieve extra fields defined for orders.
Get Order PackagesTool to download shipments previously created for a selected order.
Get Order Payments HistoryTool to retrieve payment history for a selected order, including external payment identifiers from payment gateways.
Get Order Pick Pack HistoryTool to retrieve pick and pack history for a selected order.
Get Order Printout TemplatesTool to retrieve a list of all configured printout templates available for orders.
Get Order Return Extra FieldsTool to retrieve extra fields defined for order returns.
Get Order Return Journal ListTool to download return event logs from the last 3 days in BaseLinker.
Get Order Return Payments HistoryTool to retrieve payment history for a selected order return, including external payment identifiers from the payment gateway.
Get Order Return Product StatusesTool to retrieve a list of order return product statuses from BaseLinker.
Get Order Return Reasons ListTool to retrieve a list of order return reasons.
Get Order ReturnsDownload order returns from BaseLinker return manager with optional filtering.
Get Order Return Status ListTool to retrieve order return statuses created in the BaseLinker order manager.
Get OrdersDownload orders from BaseLinker order manager with optional filtering.
Get Orders by PhoneSearch for orders associated with a specific phone number in BaseLinker.
Get Order SourcesTool to retrieve types of order sources along with their IDs from BaseLinker.
Get Order Status ListTool to retrieve a list of order statuses created in the BaseLinker order manager.
Get Order Transaction DataTool to retrieve transaction details for a selected order.
Get Package DetailsTool to get detailed information about a package.
Get PickPack CartsTool to retrieve a list of all PickPack carts belonging to the authenticated user.
Get ProtocolTool to download a parcel protocol for selected shipments.
Get ReceiptsTool to retrieve issued receipts from BaseLinker.
Get Request Parcel Pickup FieldsTool to retrieve additional fields for a parcel pickup request from a specific courier.
Get SeriesTool to download invoice/receipt numbering series.
Get Storages ListTool to download a list of available storages accessible via API.
Run Order Macro TriggerTool to run personal trigger for orders automatic actions.
Run Product Macro TriggerTool to execute a personal trigger for products automatic actions.
Run Request Parcel PickupTool to request a parcel pickup for previously created shipments.
Set Inventory Purchase Order StatusTool to change the status of a purchase order in BaseLinker inventory.
Set Order FieldsTool to edit selected fields of a specific order in BaseLinker.
Set Order PaymentTool to add a payment to an order in BaseLinker.
Set Order Product FieldsTool to edit data of selected items in a specific BaseLinker order.
Set Order ReceiptTool to mark orders with a receipt already issued.
Set Order Return FieldsTool to edit selected fields of a specific order return.
Set Order Return Product FieldsTool to edit data of selected items (e.
Set Order Return RefundTool to mark an order return as refunded in BaseLinker.
Set Order Return StatusTool to change order return status in BaseLinker.
Set Order Return StatusesTool to batch set order return statuses in BaseLinker.
Set Orders MergeTool to merge multiple orders into one, based on the selected merge mode.
Set Order StatusTool to change the status of an existing order in BaseLinker.
Set Order StatusesTool to batch update order statuses in BaseLinker.
Update Inventory Products StockTool to update stocks of products and their variants in BaseLinker catalog.

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

Prerequisites

You will need:

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

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.

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 Baselinker via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

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 Baselinker connections to use

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 Baselinker session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["baselinker"]
    )
    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 Baselinker tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to

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

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 Baselinker assistant agent with MCP tools
    agent = AssistantAgent(
        name="baselinker_assistant",
        description="An AI assistant that helps with Baselinker 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 Baselinker tools from the workbench

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Baselinker 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 Baselinker 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 Baselinker 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 Baselinker session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["baselinker"]
    )
    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 Baselinker assistant agent with MCP tools
        agent = AssistantAgent(
            name="baselinker_assistant",
            description="An AI assistant that helps with Baselinker 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 Baselinker 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 Baselinker 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 Baselinker, you can reuse the same structure for other MCP-enabled apps with minimal code changes.

How to build Baselinker MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Baselinker MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Baselinker MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Baselinker MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Baselinker MCP with Claude Cowork

Codex logo

Codex

Use Baselinker MCP with Codex

OpenClaw logo

OpenClaw

Use Baselinker MCP with OpenClaw

Hermes logo

Hermes

Use Baselinker MCP with Hermes

CLI logo

CLI

Use Baselinker MCP with CLI

Google ADK logo

Google ADK

Use Baselinker MCP with Google ADK

LangChain logo

LangChain

Use Baselinker MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Baselinker MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Baselinker MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Baselinker MCP with LlamaIndex

CrewAI logo

CrewAI

Use Baselinker MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Autogen?

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 Baselinker tools.

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

Yes, absolutely. You can configure which Baselinker 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 Baselinker 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.

Get started for freeGet a demo↗