How to Use the Salesforce MCP in OpenAI Agents SDK

Q: How do I search Salesforce records using OpenAI Agents SDK?

Use the globalsearch tool. It scans your entire CRM for matches across leads and contacts. Your agent receives the data as a structured object ready for immediate use.

Q: Can OpenAI Agents SDK perform write operations in Salesforce?

Yes. You can use createrecord, updaterecord, and deleterecord to modify your CRM state. Always verify your agent's logic before executing destructive changes.

Q: Does this MCP Server support Salesforce metadata for OpenAI Agents SDK?

Yes. Use describeobject to fetch the schema of any Salesforce object. This ensures your agent understands the required fields before it attempts to write data.

Plug your Salesforce data directly into OpenAI Agents SDK. Manage records and run queries with production-grade safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salesforce MCP to OpenAI Agents SDK

Create your Vinkius account to connect Salesforce to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salesforce with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct CRM data manipulation for OpenAI Agents SDK

Stop manual data entry. Use `create_record` and `update_record` to push changes from your agent straight into your pipeline without leaving your Python environment. Your agent handles the heavy lifting while OpenAI Agents SDK keeps the process traceable. You get full visibility into every CRM interaction from your dashboard.

Complex querying for OpenAI Agents SDK agents

Run custom logic against your CRM using `soql_query`. It handles the syntax so your agent can focus on interpreting the results for your sales team. Need a quick list? Use `list_accounts` or `list_opportunities` to fetch current status. It’s faster than waiting for a UI refresh.

Report automation with OpenAI Agents SDK

Pull insights directly from existing reports. Call `list_reports` to see what is ready, then trigger `run_report` to get the raw output. Your agent processes these results in real-time. It turns static CRM data into actionable intelligence for your workflows.

Setup guide

Set up Salesforce MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Salesforce tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Salesforce tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Salesforce tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Salesforce Agent",
            instructions="You have access to Salesforce tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Salesforce. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Salesforce now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Salesforce MCP in OpenAI Agents SDK

Use the `global_search` tool. It scans your entire CRM for matches across leads and contacts. Your agent receives the data as a structured object ready for immediate use.

Yes. You can use `create_record`, `update_record`, and `delete_record` to modify your CRM state. Always verify your agent's logic before executing destructive changes.

Yes. Use `describe_object` to fetch the schema of any Salesforce object. This ensures your agent understands the required fields before it attempts to write data.

Vinkius handles the connection using a single endpoint token. Your credentials stay isolated within the secure sandbox environment.

The server only touches the records you specifically query or modify. It doesn't store your CRM data; it acts as a direct pipe between your agent and your production instance.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript