Skip to main content
A tool for interacting with Salesforce CRM using LangChain.

​
Overview

The langchain-salesforce package integrates LangChain with Salesforce CRM, allowing you to query data, manage records, and explore object schemas from LangChain applications.

​
Key Features

  • SOQL Queries: Execute Salesforce Object Query Language (SOQL) queries
  • Object Management: Create, read, update, and delete (CRUD) operations on Salesforce objects
  • Schema Exploration: Describe object schemas and list available objects
  • Async Support: Asynchronous operation support
  • Error Handling: Detailed error messages
  • Environment Variable Support: Load credentials from environment variables

​
Setup

Install the required dependencies: 
 pip install langchain-salesforce

​
Authentication Setup

These environment variables will be automatically picked up by the integration.

​
Getting Your Security Token

If you need a security token:
  1. Log into Salesforce
  2. Go to Settings
  3. Click on “Reset My Security Token” under “My Personal Information”
  4. Check your email for the new token
Set up your Salesforce credentials as environment variables: 
export SALESFORCE_USERNAME="your-username@company.com"
export SALESFORCE_PASSWORD="your-password"
export SALESFORCE_SECURITY_TOKEN="your-security-token"
export SALESFORCE_DOMAIN="login"  # Use "test" for sandbox environments

​
Instantiation

import os

from langchain_salesforce import SalesforceTool

username = os.getenv("SALESFORCE_USERNAME", "your-username")
password = os.getenv("SALESFORCE_PASSWORD", "your-password")
security_token = os.getenv("SALESFORCE_SECURITY_TOKEN", "your-security-token")
domain = os.getenv("SALESFORCE_DOMAIN", "login")

tool = SalesforceTool(
    username=username, password=password, security_token=security_token, domain=domain
)

​
Invocation

def execute_salesforce_operation(
    operation, object_name=None, query=None, record_data=None, record_id=None
):
    """Executes a given Salesforce operation."""
    request = {"operation": operation}
    if object_name:
        request["object_name"] = object_name
    if query:
        request["query"] = query
    if record_data:
        request["record_data"] = record_data
    if record_id:
        request["record_id"] = record_id
    result = tool.invoke(request)
    return result

​
Query

This example queries Salesforce for 5 contacts. 
query_result = execute_salesforce_operation(
    operation="query", query="SELECT Id, Name, Email FROM Contact LIMIT 5"
)

​
Describe an Object

Fetches metadata for a specific Salesforce object. 
describe_result = execute_salesforce_operation(
    operation="describe", object_name="Account"
)

​
List Available Objects

Retrieves all objects available in the Salesforce instance. 
list_objects_result = execute_salesforce_operation(operation="list_objects")

​
Create a New Contact

Creates a new contact record in Salesforce. 
create_result = execute_salesforce_operation(
    operation="create",
    object_name="Contact",
    record_data={"LastName": "Doe", "Email": "doe@example.com"},
)

​
Update a Contact

Updates an existing contact record. 
update_result = execute_salesforce_operation(
    operation="update",
    object_name="Contact",
    record_id="003XXXXXXXXXXXXXXX",
    record_data={"Email": "updated@example.com"},
)

​
Delete a Contact

Deletes a contact record from Salesforce. 
delete_result = execute_salesforce_operation(
    operation="delete", object_name="Contact", record_id="003XXXXXXXXXXXXXXX"
)

​
Chaining

from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage
from langchain_salesforce import SalesforceTool

# Initialize the Salesforce tool
tool = SalesforceTool(
    username=username, password=password, security_token=security_token, domain=domain
)

# Initialize Anthropic LLM
llm = ChatAnthropic(model="claude-sonnet-4-5-20250929")

# First, let's query some contacts to get real data
contacts_query = {
    "operation": "query",
    "query": "SELECT Id, Name, Email, Phone FROM Contact LIMIT 3",
}

contacts_result = tool.invoke(contacts_query)

# Now let's use the LLM to analyze and summarize the contact data
if contacts_result and "records" in contacts_result:
    contact_data = contacts_result["records"]

    # Create a message asking the LLM to analyze the contact data
    analysis_prompt = f"""
    Please analyze the following Salesforce contact data and provide insights:

    Contact Data: {contact_data}

    Please provide:
    1. A summary of the contacts
    2. Any patterns you notice
    3. Suggestions for data quality improvements
    """

    message = HumanMessage(content=analysis_prompt)
    analysis_result = llm.invoke([message])

    print("\nLLM Analysis:")
    print(analysis_result.content)

​
API reference

For comprehensive documentation and API reference, see:

​
Additional Resources

Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.