Salesforce MCP Server for OpenAI Agents SDK 12 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Salesforce through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="Salesforce Assistant",
instructions=(
"You help users interact with Salesforce. "
"You have access to 12 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Salesforce"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Salesforce MCP Server
Connect your Salesforce CRM to any AI agent and manage your entire sales pipeline through natural conversation.
The OpenAI Agents SDK auto-discovers all 12 tools from Salesforce through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Salesforce, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- SOQL Queries — Execute any SOQL query to retrieve data across all objects
- Account Management — List, view, create, and update accounts
- Contact & Lead Management — Browse contacts, search across all objects
- Opportunity Tracking — Monitor pipeline, create and update deals
- Reports — List and execute Salesforce reports
- Full CRUD — Create, read, update, and delete any SObject type
- Global Search — Full-text search across all Salesforce data
The Salesforce MCP Server exposes 12 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Salesforce to OpenAI Agents SDK via MCP
Follow these steps to integrate the Salesforce MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 12 tools from Salesforce
Why Use OpenAI Agents SDK with the Salesforce MCP Server
OpenAI Agents SDK provides unique advantages when paired with Salesforce through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Salesforce + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Salesforce MCP Server delivers measurable value.
Automated workflows: build agents that query Salesforce, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Salesforce, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Salesforce tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Salesforce to resolve tickets, look up records, and update statuses without human intervention
Salesforce MCP Tools for OpenAI Agents SDK (12)
These 12 tools become available when you connect Salesforce to OpenAI Agents SDK via MCP:
create_record
Provide JSON fields as a string. Create a new Salesforce record
delete_record
This action is irreversible. Delete a Salesforce record
describe_object
Useful for understanding data structure. Get metadata about a Salesforce object
get_record
Specify the SObject type (Account, Contact, Opportunity, Case, Lead) and the record ID. Get a specific Salesforce record by type and ID
global_search
Returns matches across Accounts, Contacts, Leads, and other objects simultaneously. Search across all Salesforce objects
list_accounts
List Salesforce accounts
list_contacts
List Salesforce contacts
list_opportunities
List sales opportunities
list_reports
List available Salesforce reports
run_report
Use list_reports first to find the report ID. Execute a Salesforce report and get results
soql_query
Example: SELECT Id, Name FROM Account WHERE Industry = 'Technology' LIMIT 10 Execute a SOQL query against Salesforce
update_record
Provide the SObject type, ID, and JSON fields to update. Update an existing Salesforce record
Example Prompts for Salesforce in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Salesforce immediately.
"Show me all open opportunities worth over $50,000."
"Create a new lead for John Smith from TechCo, email john@techco.com."
"Run the Monthly Sales Report."
Troubleshooting Salesforce MCP Server with OpenAI Agents SDK
Common issues when connecting Salesforce to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Salesforce + OpenAI Agents SDK FAQ
Common questions about integrating Salesforce MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect Salesforce with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Salesforce to OpenAI Agents SDK
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.