How to integrate Salesforce service cloud MCP with Autogen

This guide walks you through connecting Salesforce service cloud to AutoGen using the Composio tool router. By the end, you'll have a working Salesforce service cloud agent that can list all open support cases for today, update case status to resolved for customer, fetch recent customer interactions for an account through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Salesforce service cloud account through Composio's Salesforce service cloud 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
Salesforce service cloud logoSalesforce service cloud
Oauth2

Salesforce Service Cloud is a customer service platform for case management, omnichannel support, and automation. It enables teams to deliver faster, personalized service experiences with robust workflow tools and a unified workspace.

23 Tools

Introduction

This guide walks you through connecting Salesforce service cloud to AutoGen using the Composio tool router. By the end, you'll have a working Salesforce service cloud agent that can list all open support cases for today, update case status to resolved for customer, fetch recent customer interactions for an account through natural language commands.

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

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

Also integrate Salesforce service cloud with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle 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 Salesforce service cloud
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Salesforce service cloud tools
  • Run a live chat loop where you ask the agent to perform Salesforce service cloud 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 Salesforce service cloud MCP server, and what's possible with it?

The Salesforce service cloud MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Salesforce Service Cloud account. It provides structured and secure access to your customer service data, so your agent can perform actions like managing cases, retrieving knowledge articles, automating service processes, and tracking customer interactions on your behalf.

  • Case management and triage: Empower your agent to create, update, assign, or close customer service cases, ensuring timely resolution of inquiries and incidents.
  • Knowledge base retrieval: Let your agent search, read, and recommend relevant knowledge articles to assist with customer support and internal troubleshooting.
  • Customer interaction tracking: Have your agent log new interactions, fetch historical communication, and surface recent touchpoints for a full view of customer engagement.
  • Omnichannel support automation: Enable your agent to route cases, escalate issues, and manage service requests across chat, email, phone, and social channels all from one place.
  • Service workflow automation: Direct your agent to trigger macros, update case statuses, or launch automated actions to streamline repetitive tasks and boost support team productivity.

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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["salesforce_service_cloud"]
    )
    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 Salesforce service cloud 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 Salesforce service cloud assistant agent with MCP tools
    agent = AssistantAgent(
        name="salesforce_service_cloud_assistant",
        description="An AI assistant that helps with Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["salesforce_service_cloud"]
    )
    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 Salesforce service cloud assistant agent with MCP tools
        agent = AssistantAgent(
            name="salesforce_service_cloud_assistant",
            description="An AI assistant that helps with Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud 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 Salesforce service cloud, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Salesforce service cloud action and event your agent gets out of the box.

Chasitor Sneak Peek

Send real-time typing indicator (sneak peek) to Live Agent during active chat session.

Composite Batch

Tool to execute multiple independent REST subrequests in one batch call.

Composite Request

Execute up to 25 dependent Salesforce REST subrequests in a single API call.

Composite SObject Tree

Create one or more nested sObject record trees in a single API call.

Create Case Record

Tool to create or upsert a Salesforce Case record.

Delete Case Record

Tool to delete a Salesforce Case record.

Describe SObject

Tool to retrieve metadata of any sObject.

Generate Request ID

Generate a UUIDv4 string to use as an Idempotency-Key header in Salesforce User Interface API requests.

Generate Signed JWT Assertion

Tool to generate a signed JWT assertion for Salesforce JWT bearer OAuth flow.

Get Case Record

Retrieve a Salesforce Case record by its ID.

Get Chat Messages

Tool to long-poll for chat messages/events.

Get Live Agent API Version

Tool to retrieve current Live Agent API version.

List Einstein Bots

Lists all Einstein Bot definitions in the Salesforce organization.

Query All SOQL

Tool to execute a SOQL query including deleted and archived records.

Query SOQL

Tool to execute a SOQL query.

Reconnect Chat Session

Tool to reconnect a Live Agent chat session after the affinity token changes.

Resync Chasitor State

Resynchronizes the chat visitor's state after a session reconnection.

Retrieve Connected App Private Key

Tool to retrieve RSA private key PEM for a Salesforce Connected App.

Retrieve Salesforce Username

Tool to retrieve the Salesforce username.

Send Custom Event

Send a custom event from a chat visitor to a Live Agent during an active chat session.

Set Breadcrumb

Tool to set a breadcrumb URL for the visitor's current page.

Upload File to S3

Tool to upload a file to managed S3 storage.

Visitor Sensitive Data Rule Triggered

Tool to trigger sensitive data rules for the chat visitor.

FRAMEWORKS

How to build Salesforce service cloud MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Salesforce service cloud MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Salesforce service cloud MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Salesforce service cloud MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Salesforce service cloud MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Salesforce service cloud MCP with Claude Cowork

Codex logo

Codex

Use Salesforce service cloud MCP with Codex

Cursor logo

Cursor

Use Salesforce service cloud MCP with Cursor

OpenClaw logo

OpenClaw

Use Salesforce service cloud MCP with OpenClaw

Hermes logo

Hermes

Use Salesforce service cloud MCP with Hermes

CLI logo

CLI

Use Salesforce service cloud MCP with CLI

Google ADK logo

Google ADK

Use Salesforce service cloud MCP with Google ADK

LangChain logo

LangChain

Use Salesforce service cloud MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Salesforce service cloud MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Salesforce service cloud MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Salesforce service cloud MCP with LlamaIndex

CrewAI logo

CrewAI

Use Salesforce service cloud MCP with CrewAI

OpenCode logo

OpenCode

Use Salesforce service cloud MCP with OpenCode

VS Code logo

VS Code

Use Salesforce service cloud MCP with VS Code

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Salesforce service cloud 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 Salesforce service cloud data and credentials are handled as safely as possible.

Start with Salesforce service cloud.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Salesforce service cloud 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