Salesforce Sales Cloud MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Salesforce Sales Cloud 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 Sales Cloud Assistant",
instructions=(
"You help users interact with Salesforce Sales Cloud. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Salesforce Sales Cloud"
)
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 Sales Cloud MCP Server
Connect Salesforce Sales Cloud to any AI agent — instant access to your CRM data without switching tabs.
The OpenAI Agents SDK auto-discovers all 10 tools from Salesforce Sales Cloud through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Salesforce Sales Cloud, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Leads — Search, create, update, and qualify leads by name, email, or company
- Opportunities — Track deals, update stages, amounts, and close dates
- Accounts — Look up company details including revenue, industry, and employees
- Contacts — Find contacts by name or email with account associations
- Activities — Log calls, meetings, and emails as Tasks linked to records
- Pipeline — Get an instant summary of your open pipeline by stage
The Salesforce Sales Cloud MCP Server exposes 10 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 Sales Cloud to OpenAI Agents SDK via MCP
Follow these steps to integrate the Salesforce Sales Cloud 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 10 tools from Salesforce Sales Cloud
Why Use OpenAI Agents SDK with the Salesforce Sales Cloud MCP Server
OpenAI Agents SDK provides unique advantages when paired with Salesforce Sales Cloud 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 Sales Cloud + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Salesforce Sales Cloud MCP Server delivers measurable value.
Automated workflows: build agents that query Salesforce Sales Cloud, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Salesforce Sales Cloud, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Salesforce Sales Cloud tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Salesforce Sales Cloud to resolve tickets, look up records, and update statuses without human intervention
Salesforce Sales Cloud MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect Salesforce Sales Cloud to OpenAI Agents SDK via MCP:
sf_create_lead
lastName and company are required fields in Salesforce. Status defaults to "Open - Not Contacted". Once qualified, leads can be converted to Contact + Account + Opportunity in the Salesforce UI. Returns the created lead with its 18-character Salesforce ID. Create a new lead in Salesforce Sales Cloud with name, company, email, phone, title, and initial status
sf_log_activity
Link to a person via whoId (Contact or Lead ID) and/or to a record via whatId (Account or Opportunity ID). Status defaults to "Completed". Priority: High, Normal, Low. Use to log completed calls, meetings, or emails for activity tracking and reporting. Log a call, meeting, or email as a completed Task in Salesforce linked to a contact, lead, account, or opportunity
sf_opportunities_by_stage
Returns deals sorted by amount descending. Standard stages: Prospecting, Qualification, Needs Analysis, Value Proposition, Id. Decision Makers, Perception Analysis, Proposal/Price Quote, Negotiation/Review, Closed Won, Closed Lost. Use for questions like "what deals are in Negotiation?" or "total value of Closed Won this quarter." Get all Salesforce opportunities at a specific pipeline stage for bottleneck analysis, forecasting, or stage review
sf_pipeline_summary
Returns the number of deals and total monetary value at each stage. Perfect for pipeline health checks, forecasting conversations, and identifying bottleneck stages. Use when the user asks "how is the pipeline?", "what is our total pipeline value?", or "which stage has the most deals?" Get an aggregate snapshot of the open sales pipeline — deal count and total value per stage for a quick health check
sf_search_accounts
Returns account name, industry, annual revenue, number of employees, phone, website, billing city/state/country, and owner. Accounts are the company-level records that contacts and opportunities are linked to. Use when the user asks about a company or needs account-level data. Search Salesforce accounts (companies) by name to find organizations with industry, revenue, employee count, and location
sf_search_contacts
Returns contact name, email, phone, account name, title, department, and mailing address. Contacts are qualified individuals linked to accounts — different from leads (unqualified prospects). Use when the user asks about a specific customer contact. Search Salesforce contacts by name or email to find people at customer accounts with title, department, and phone
sf_search_leads
Returns lead name, company, email, phone, title, status (e.g., Open - Not Contacted, Working, Closed - Converted), rating (Hot/Warm/Cold), lead source, and assigned owner. Use when the user wants to find a specific prospect, check lead status, or review unqualified pipeline. Search Salesforce leads by name, email, or company to find prospective customers in the sales pipeline
sf_search_opportunities
Returns opportunity name, stage (Prospecting/Qualification/Needs Analysis/Value Proposition/Id. Decision Makers/Perception Analysis/Proposal/Negotiation/Closed Won/Closed Lost), amount, close date, probability percentage, and assigned owner. Use for pipeline review, deal lookup, or forecasting queries. Search Salesforce opportunities by name to find deals with stage, amount, probability, close date, and owner
sf_update_lead
Only specified fields are updated. Common operations: change Status to "Working" or "Closed - Converted", set Rating to Hot/Warm/Cold for prioritization, or update contact details. Requires the 18-character Salesforce ID. Update an existing Salesforce lead — change status, rating, contact info, or other fields to reflect qualification progress
sf_update_opportunity
Common operations: advance StageName when deal progresses, update Amount after negotiation, push CloseDate when timeline shifts, set StageName to "Closed Won"/"Closed Lost" to close. Only specified fields change. Update a Salesforce opportunity — advance stage, change amount, update close date, or add notes to reflect deal progress
Example Prompts for Salesforce Sales Cloud in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Salesforce Sales Cloud immediately.
"Show me all hot leads from this week"
"What does my pipeline look like right now?"
"Create a new lead: John Smith from Acme Corp, john@acme.com"
Troubleshooting Salesforce Sales Cloud MCP Server with OpenAI Agents SDK
Common issues when connecting Salesforce Sales Cloud to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
Salesforce Sales Cloud + OpenAI Agents SDK FAQ
Common questions about integrating Salesforce Sales Cloud 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 Sales Cloud 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 Sales Cloud to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.
