How to Connect OpenAI to Real-Time SaaS Data with Unified.to MCP Server
August 28, 2025
OpenAI's LLMs can power rich workflows — but most products still need access to live customer data from CRMs, ATSs, HRIS, or accounting systems. That usually means writing brittle glue code, normalizing APIs, and maintaining webhook jobs.
With Unified.to's MCP server, you can skip that complexity. Unified.to exposes 2300 SaaS integrations as real-time, callable tools that OpenAI can use directly — no custom integration logic required.
In this guide, we'll walk through how to connect OpenAI to Unified.to MCP so your application can give OpenAI real-time access to customer SaaS data and actions.
Authentication
Every tool call to the Unified.to MCP server needs a credential. Send it in the Authorization: Bearer {token} header (or x-api-key). Passing the token as a URL parameter is deprecated.
Unified.to documents five authentication options. Two fit an OpenAI integration:
- Private (workspace key + connection)
Use your Unified.to workspace API key and add aconnectionparameter. This should never be exposed publicly. - Connection-scoped token
Generate a connection-scoped token with the Core MCP toolget_unified_connection_mcp_urlandmode=user; use therecommendedURL and headers it returns. The token grants one connection only, never carries your workspace API key and doesn't expire; revoke it by deleting the connection.mode=apiuses your workspace API key and must not be shared.
Integrating with OpenAI (LLM API)
Once your MCP client is set up, you can connect it to OpenAI's API, which natively supports remote MCP servers.
Configure OpenAI to Use Unified MCP
Model names change often; use a current model from your provider's model list.
When you send a Responses API request, add Unified MCP as a remote MCP tool ("type": "mcp"). OpenAI calls the MCP server on your behalf, so pass a connection-scoped signed token (works for one connection only) in the authorization field and keep your workspace API key on your server.
Here's a candidate assessment example:
import os
from openai import OpenAI
# Connection-scoped signed token from get_unified_connection_mcp_url (mode=user)
UNIFIED_MCP_TOKEN = os.environ["UNIFIED_MCP_TOKEN"]
CONNECTION_ID = os.environ["CONNECTION_ID"]
# Regional host without a path: US https://mcp-api.unified.to, EU https://mcp-api-eu.unified.to, AU https://mcp-api-au.unified.to
UNIFIED_MCP_URL = os.environ.get("UNIFIED_MCP_URL", "https://mcp-api.unified.to")
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(
model="gpt-6-astra",
tools=[{
"type": "mcp",
"server_label": "unified",
"server_url": f"{UNIFIED_MCP_URL}/mcp?connection={CONNECTION_ID}",
"authorization": UNIFIED_MCP_TOKEN,
"require_approval": "never",
}],
input="Score this candidate for the Software Engineer job.",
)
print(response.output_text)
OpenAI lists and calls the Unified MCP tools itself, so no backend glue code is required.
Advanced MCP Options
Unified.to MCP gives you granular control over how tools are exposed to OpenAI:
permissions→ restrict available scopes.tools→ allowlist specific tool IDs.aliases→ adds extra descriptions to improve tool matching.hide_sensitive=true→ strips sensitive (PII) fields such as names, emails, phone numbers, addresses, date of birth, SSN/SIN and compensation, plus credential fields, from results.include_external_tools=true→ expose all vendor API endpoints, not just Unified.to's normalized models.
These options help you keep OpenAI outputs predictable and secure in production-grade workflows.
Sample Snippet
import OpenAI from 'openai';
// OpenAI model
const model = 'gpt-6-astra';
// Unified connection ID that the MCP server should use
const connection = process.env.CONNECTION_ID;
// Regional host without a path: US https://mcp-api.unified.to, EU https://mcp-api-eu.unified.to, AU https://mcp-api-au.unified.to
const UNIFIED_MCP_URL = process.env.UNIFIED_MCP_URL || 'https://mcp-api.unified.to';
// Set to true to expose the vendor's own API endpoints as tools
const includeExternal = false;
const message = 'Score this candidate for the Software Engineer job.';
// Optional: list of specific tools that you want to use
const toolIds = ['get_messaging_message','list_messaging_message']
const openai = new OpenAI({
apiKey: process.env.OPENAI_API_KEY || '',
});
const params = new URLSearchParams({
connection,
include_external_tools: includeExternal ? 'true' : 'false',
});
if (toolIds.length > 0) {
params.append('tools', toolIds.join(','));
}
const serverUrl = `${UNIFIED_MCP_URL}/mcp?${params.toString()}`;
const completion = await openai.responses.create({
model,
tools: [
{
type: 'mcp',
server_label: 'unifiedMCP',
server_url: serverUrl, // change url as needed
// Connection-scoped signed token (one connection only)
authorization: process.env.UNIFIED_MCP_TOKEN,
require_approval: 'never',
},
],
instructions: `You are a helpful assistant`,
input: message,
});
console.log(completion.output_text);
Coverage and Infrastructure
Unified.to MCP runs as part of the Unified API:
- 242,210 real-time tools (growing weekly)
- 2300 integrations across 39 categories (ATS, CRM, HRIS, Accounting, Messaging, File Storage, and more)
- No stored customer records: Unified.to stores no customer records; logs hold operational metadata only
- Scoped security controls — permissions, aliases, and PII redaction
- Multi-region deployment — US, EU, and AU data centers for compliance
This ensures your OpenAI workflows aren't just demos — they're secure, scalable, and designed for production-grade use cases.
Unified.to MCP works with major LLM providers, including OpenAI, Anthropic, Google Gemini and Cohere. That means you can build once and connect to any agent client.