Case Study How Interstellar Labs Scaled Their Agent Platform to Enterprise with Unified.to
Unified.to
All articles

How to Connect Cohere to Real-Time SaaS Data with Unified.to MCP Server

September 16, 2025

Cohere'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 317+ SaaS integrations as real-time, callable tools that Cohere can use directly — no custom integration logic required.

In this guide, we'll walk through how to connect Cohere to Unified.to MCP so your application can give Cohere real-time access to customer SaaS data and actions.

Authentication

Every request to the Unified.to MCP server must include a token. You can pass this either as a URL parameter (?token=...) or in the Authorization: bearer {token} header.

There are two authentication flows:

  • Private (workspace key + connection)
    Use your Unified.to workspace API key and add a connection parameter. This should never be exposed publicly.
  • Public (end-user safe)
    Generate a token in the format {connectionID}-{nonce}-{signature} using your workspace secret. Safe to share with customers.

Integrating Unified.to MCP Server with Cohere

Cohere's chat API can directly consume tools defined by Unified.to MCP.

Manual Tool Orchestration:

  1. Call Unified's /tools?type=cohere endpoint and pass the tool list to Cohere:
    response = co.chat(
    model="command-a-03-2025", messages=messages, tools=tools
)
  2. When Cohere requests a tool call, call Unified's /tools/{id}/call endpoint.
  3. Pass the tool result back to Cohere in your next message

Example Prompt and Response

Prompt:

"Score this candidate for the Software Engineer job."

What happens:

  • Cohere discovers the available tools from Unified MCP (e.g., fetch-candidate, fetch-job, score-candidate).
  • Cohere calls fetch-candidate and fetch-job tools to get the data.
  • Cohere calls score-candidate with the data.
  • Cohere returns a response like:

Response:

Candidate Jane Doe scored 92/100 for the Software Engineer job. Strengths: Python, distributed systems. Recommended for interview.

Advanced MCP Options

Unified.to MCP gives you granular control over how tools are exposed to Cohere:

  • permissions → restrict available scopes.
  • tools → allowlist specific tool IDs.
  • aliases → add synonyms so Cohere better matches tool names.
  • hide_sensitive=true → automatically strip PII (emails, phone numbers, etc).
  • include_external_tools=true → expose all vendor API endpoints, not just Unified.to's normalized models.

These options help you keep Cohere outputs predictable and secure in production-grade workflows.

Sample Snippet

import { CohereClientV2 } from 'cohere-ai';

// Unified connection Id that you want to have the mcp to use tools for
const connection = 'UNIFIED_CONNECTION_ID';
 // location from where your unified account was created
const dc = 'us';
// Optional: list of specific tools that you want to use
const toolIds = ['get_messaging_message','list_messaging_message']
const cohereClient = new CohereClientV2({
    token: process.env.COHERE_API_KEY || '',
});

const params = new URLSearchParams({
    token: process.env.UNIFIED_API_KEY || '',
    connection,
    type: 'cohere',
    dc,
    include_external_tools: includeExternal ? 'true' : 'false',
});

if (toolIds.length > 0) {
    params.append('tools', toolIds.join(','));
}

const tools = await fetch(`${process.env.UNIFIED_MCP_URL}/tools?${params.toString()}`);
const toolsJson = await tools.json();
const completion = await cohereClient.chat({
    model: 'command-a-03-2025',
    messages: [
        {
            role: 'user',
            content: message,
        },
    ],
    tools: toolsJson,
});


for (const toolCall of completion?.message?.toolCalls || []) {
    // call mcp server with toolCallId
    const toolCallResponse = await fetch(`${process.env.UNIFIED_MCP_URL}/mcp/tools/${toolCall.function?.name}/call?${params.toString()}`, {
        method: 'POST',
        body: toolCall.function?.arguments || '{}',
    });
    const toolCallResponseJson = await toolCallResponse.json();
    console.log(JSON.stringify(toolCallResponseJson, null, 2));
}

The Most Complete MCP Server for AI-Native Teams

Unified.to MCP is the most complete hosted MCP server available today:

  • 20,082+ real-time tools (growing weekly)
  • 335+ integrations across 21 categories (ATS, CRM, HRIS, Accounting, Messaging, File Storage, and more)
  • Zero-storage architecture — no caching, no liability
  • Scoped security controls — permissions, aliases, and PII redaction
  • Multi-region deployment — US, EU, and AU data centers for compliance

This ensures your Cohere workflows aren't just demos — they're secure, scalable, and designed for production-grade use cases.

Next Steps

Unified.to MCP works across all major LLM providers: OpenAI, Anthropic, Google Gemini and Cohere. That means you can build once and connect to any agent client.

Explore the MCP docs or book a demo to see it live in action.

Note: Unified.to MCP is currently in beta and should not be used in production systems yet. Contact us if you'd like to explore production use.

All articles