Salesforce Service Cloud MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Salesforce Service 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 Service Cloud Assistant",
instructions=(
"You help users interact with Salesforce Service Cloud. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from Salesforce Service 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 Service Cloud MCP Server
Connect Salesforce Service Cloud to any AI agent.
The OpenAI Agents SDK auto-discovers all 8 tools from Salesforce Service Cloud through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Salesforce Service Cloud, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Cases — Search, create, update, and filter by status or priority
- Comments — Read and add internal/public case comments
- Knowledge — Search published knowledge articles for instant answers
- Metrics — Aggregate case counts by status and priority
The Salesforce Service Cloud MCP Server exposes 8 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 Service Cloud to OpenAI Agents SDK via MCP
Follow these steps to integrate the Salesforce Service 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 8 tools from Salesforce Service Cloud
Why Use OpenAI Agents SDK with the Salesforce Service Cloud MCP Server
OpenAI Agents SDK provides unique advantages when paired with Salesforce Service 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 Service Cloud + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the Salesforce Service Cloud MCP Server delivers measurable value.
Automated workflows: build agents that query Salesforce Service Cloud, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries Salesforce Service Cloud, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through Salesforce Service Cloud tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query Salesforce Service Cloud to resolve tickets, look up records, and update statuses without human intervention
Salesforce Service Cloud MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect Salesforce Service Cloud to OpenAI Agents SDK via MCP:
sf_add_case_comment
Set isPublished to true if the comment should be visible to the customer (e.g., in a customer portal). Default is internal-only. Use to log agent responses, internal notes, or resolution steps on a support case. Add a comment to a Salesforce case — internal note or customer-visible response
sf_case_comments
Returns comment body, whether it is published (customer-visible), creator name, and creation date. Comments provide the full conversation history of a support case. Use to review case discussions or get context before responding. Get all comments (internal and customer-visible) on a specific Salesforce case for case history review
sf_case_metrics
Returns summary data: how many cases at each status × priority intersection. Perfect for support team dashboards, capacity planning, and identifying volume trends. Use when the user asks "how many open cases do we have?" or "what is the case breakdown by priority?" Get aggregate support case metrics — case counts grouped by status and priority for a team dashboard view
sf_cases_by_status
Returns cases sorted by priority then creation date. Use for support queue management: "how many new cases are there?", "show escalated cases", or for case workload analysis by status. Get all Salesforce cases at a specific status for queue analysis — New, Working, Escalated, or Closed
sf_create_case
Subject is required. Status defaults to "New". Priority: High, Medium, Low. Origin: Web, Phone, Email. Link to a customer via contactId and their company via accountId (both use 18-char Salesforce IDs). Cases track the complete lifecycle of a customer support issue. Create a new support case in Salesforce Service Cloud with subject, description, priority, origin, and linked contact/account
sf_search_cases
Returns case number, subject, status (New/Working/Escalated/Closed), priority (High/Medium/Low), origin channel (Web/Phone/Email), case owner, and description. Use when the user wants to find a specific support case, look up a case number, or review customer issues. Search Salesforce Service Cloud cases by subject or case number to find customer support issues
sf_search_knowledge
Returns article title, summary, URL, and article type. Salesforce Knowledge is the built-in KB for self-service and agent-assist. Use when the user asks for help articles, documented solutions, or wants to check if an issue has been addressed in the knowledge base. Search the Salesforce Knowledge Base for published articles to find documented solutions and answers
sf_update_case
Common operations: advance Status from "New" to "Working" to "Closed", escalate Priority to "High", or append to Description. Only specified fields change. Update a Salesforce case — change status, escalate priority, or add description to reflect case progress
Example Prompts for Salesforce Service Cloud in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Salesforce Service Cloud immediately.
"How many open P1 cases do we have?"
"Find a knowledge article about password reset"
"Create a high-priority case: Login page returning 500 error"
Troubleshooting Salesforce Service Cloud MCP Server with OpenAI Agents SDK
Common issues when connecting Salesforce Service 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 Service Cloud + OpenAI Agents SDK FAQ
Common questions about integrating Salesforce Service 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 Service 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 Service Cloud to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.