How to integrate Salesforce MCP with Autogen

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Salesforce Logo
AutoGen Logo
divider

Introduction

This guide walks you through connecting Salesforce to AutoGen using the Composio tool router. By the end, you'll have a working Salesforce agent that can add new contact to spring campaign, clone opportunity with all associated products, complete follow-up task for lead smith, associate contact jane doe to acme account through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Salesforce account through Composio's Salesforce 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 required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Salesforce
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Salesforce tools
  • Run a live chat loop where you ask the agent to perform Salesforce 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 MCP server, and what's possible with it?

The Salesforce 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 account. It provides structured and secure access to your CRM data, so your agent can perform actions like managing contacts, handling opportunities, automating campaigns, and tracking tasks on your behalf.

  • Automated contact and lead management: Effortlessly create new accounts, add contacts or leads to campaigns, and associate contacts with accounts to keep your CRM data up-to-date.
  • Streamlined opportunity management: Let your agent clone opportunities, add products to deals, and manage the full sales cycle for your pipeline.
  • Intelligent campaign automation: Enable your agent to create campaigns, enroll contacts or leads, and track campaign engagement for more effective marketing.
  • Task completion and workflow efficiency: Have your agent mark Salesforce tasks as completed and update records, keeping your team on track without manual intervention.
  • Flexible record operations: Allow the agent to clone existing records or apply lead assignment rules, ensuring data consistency and smart routing across your Salesforce environment.

Supported Tools & Triggers

Tools
Triggers
Add contact to campaignAdds a contact to a campaign by creating a campaignmember record, allowing you to track campaign engagement.
Add lead to campaignAdds a lead to a campaign by creating a campaignmember record, allowing you to track campaign engagement.
Add product to opportunityAdds a product (line item) to an opportunity.
Apply lead assignment rulesApplies configured lead assignment rules to a specific lead, automatically routing it to the appropriate owner based on your organization's rules.
Associate contact to accountAssociates a contact with an account by updating the contact's accountid field.
Clone opportunity with productsClones an opportunity and optionally its products (line items).
Clone recordCreates a copy of an existing salesforce record by reading its data, removing system fields, and creating a new record.
Complete taskMarks a task as completed with optional completion notes.
Create accountCreates a new account in salesforce with the specified information.
Create campaignCreates a new campaign in salesforce with the specified information.
Create contactCreates a new contact in salesforce with the specified information.
Create leadCreates a new lead in salesforce with the specified information.
Create noteCreates a new note attached to a salesforce record with the specified title and content.
Create opportunityCreates a new opportunity in salesforce with the specified information.
Create taskCreates a new task in salesforce to track activities, to-dos, and follow-ups related to contacts, leads, or other records.
Delete accountPermanently deletes an account from salesforce.
Delete campaignPermanently deletes a campaign from salesforce.
Delete contactPermanently deletes a contact from salesforce.
Delete leadPermanently deletes a lead from salesforce.
Delete notePermanently deletes a note from salesforce.
Delete opportunityPermanently deletes an opportunity from salesforce.
Get accountRetrieves a specific account by id from salesforce, returning all available fields.
Get campaignRetrieves a specific campaign by id from salesforce, returning all available fields.
Get contactRetrieves a specific contact by id from salesforce, returning all available fields.
Get dashboardGets detailed metadata for a specific dashboard including its components, layout, and filters.
Get leadRetrieves a specific lead by id from salesforce, returning all available fields.
Get noteRetrieves a specific note by id from salesforce, returning all available fields.
Get opportunityRetrieves a specific opportunity by id from salesforce, returning all available fields.
Get report metadataGets detailed metadata for a specific report including its structure, columns, filters, and groupings.
Get report instance resultsGets the results of a report instance created by running a report.
Get user infoRetrieves information about the current user or a specific user in salesforce.
List accountsLists accounts from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List campaignsLists campaigns from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List contactsLists contacts from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List dashboardsLists all dashboards available in salesforce with basic metadata including name, id, and urls.
List email templatesLists available email templates in salesforce with filtering and search capabilities.
List leadsLists leads from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List notesLists notes from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List opportunitiesLists opportunities from salesforce using soql query, allowing flexible filtering, sorting, and field selection.
List reportsLists all reports available in salesforce with basic metadata including name, id, and urls.
Log callLogs a completed phone call as a task in salesforce with call-specific details like duration, type, and disposition.
Log email activityCreates an emailmessage record to log email activity in salesforce, associating it with related records.
Mass transfer ownershipTransfers ownership of multiple records to a new owner in a single operation using salesforce's composite api for better performance.
Remove from campaignRemoves a lead or contact from a campaign by deleting the campaignmember record.
Run reportRuns a report and returns the results.
Run SOQL queryExecutes a soql query against salesforce data.
Search accountsSearch for salesforce accounts using multiple criteria like name, industry, type, location, or contact information.
Search campaignsSearch for salesforce campaigns using multiple criteria like name, type, status, date range, or active status.
Search contactsSearch for salesforce contacts using multiple criteria like name, email, phone, account, or title.
Search leadsSearch for salesforce leads using multiple criteria like name, email, phone, company, title, status, or lead source.
Search notesSearch for salesforce notes using multiple criteria like title, body content, parent record, owner, or creation date.
Search opportunitiesSearch for salesforce opportunities using multiple criteria like name, account, stage, amount, close date, or status.
Search tasksSearch for salesforce tasks using multiple criteria like subject, status, priority, assigned user, related records, or dates.
Send emailSends an email through salesforce with options for recipients, attachments, and activity logging.
Send email from templateSends an email using a predefined salesforce email template with merge field support.
Send mass emailSends bulk emails to multiple recipients, either using a template or custom content.
Update accountUpdates an existing account in salesforce with the specified changes.
Update campaignUpdates an existing campaign in salesforce with the specified changes.
Update contactUpdates an existing contact in salesforce with the specified changes.
Update leadUpdates an existing lead in salesforce with the specified changes.
Update noteUpdates an existing note in salesforce with the specified changes.
Update opportunityUpdates an existing opportunity in salesforce with the specified changes.
Update taskUpdates an existing task in salesforce with new information.

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

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Salesforce 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 Salesforce 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 Salesforce 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 Salesforce session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["salesforce"]
    )
    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 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 Salesforce assistant agent with MCP tools
    agent = AssistantAgent(
        name="salesforce_assistant",
        description="An AI assistant that helps with Salesforce 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 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 Salesforce 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 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 and AutoGen:

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

How to build Salesforce MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Salesforce MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Salesforce MCP with Claude Agent SDK

Google ADK

Google ADK

Use Salesforce MCP with Google ADK

LangChain

LangChain

Use Salesforce MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Salesforce MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Salesforce MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Salesforce MCP with LlamaIndex

CrewAI

CrewAI

Use Salesforce MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Salesforce 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 Salesforce 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