Skip to main content

​
MCP Integration

MCP (Model Context Protocol) allows your AI voice agents to access external tools and systems in real-time during calls. Agents can query databases, update CRMs, check calendars, and more—all while speaking with the customer.

​
What is MCP?

MCP is an open protocol that lets AI models interact with external tools. Instead of hard-coding integrations, you connect an MCP server, and your agents automatically discover and use available tools. Example: Connect an MCP server for your CRM, and your agent can:
  • Look up customer information by phone number
  • Check order status during the call
  • Update contact records after qualifying a lead

​
How MCP Works in EolasFlow

1

Connect MCP Server

You register an MCP server (your tools endpoint).
2

Enable on Campaign

You enable MCP on a campaign and select your server.
3

Tool Discovery

When a call starts, EolasFlow connects to your MCP server and discovers available tools.
4

Agent Uses Tools

During the call, your AI agent can call any discovered tool as needed.
5

Results Spoken

Tool results are processed by the AI and spoken to the customer.

​
Setting Up MCP

​
Step 1: Register an MCP Server

1

Navigate to Integrations

Go to Dashboard → Integrations → MCP Servers.
2

Add New Server

Click Add Server and enter:
  • Name: A descriptive name (e.g., “CRM Tools”)
  • URL: Your MCP server’s SSE endpoint
3

Configure Authentication (Optional)

If your server requires authentication, add an API key. It’s sent as a Bearer token.
4

Preview Tools

Click Preview to discover available tools without saving.
5

Review Tools

See the list of tools your server provides with their descriptions and parameters.
6

Save Server

Click Save to register the server.

​
Step 2: Enable MCP on a Campaign

1

Open Campaign Settings

Go to Dashboard → Campaigns and click on your campaign.
2

Navigate to MCP Tab

Click the MCP tab in campaign settings.
3

Enable MCP

Toggle MCP On and select your registered server.
4

Configure Timeout (Optional)

Adjust the tool execution timeout if needed (default: 5 seconds).
5

Save Configuration

Click Save. Your agent now has access to MCP tools during calls.

​
MCP Server Requirements

Your MCP server must:
  • Support SSE (Server-Sent Events) transport
  • Implement the JSON-RPC 2.0 protocol
  • Handle these methods:
    • initialize - Establish connection
    • tools/list - Return available tools
    • tools/call - Execute a tool

​
Tool Definition Format

Your server returns tools in this format: 
{
  "tools": [
    {
      "name": "get_customer",
      "description": "Look up customer by phone number",
      "inputSchema": {
        "type": "object",
        "properties": {
          "phone": {
            "type": "string",
            "description": "Customer phone number"
          }
        },
        "required": ["phone"]
      }
    }
  ]
}

​
Tool Execution

When the AI calls a tool, your server receives: 
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "get_customer",
    "arguments": {
      "phone": "+15551234567"
    }
  },
  "id": 123
}
Your server responds with: 
{
  "jsonrpc": "2.0",
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Customer: John Smith, Status: Premium, Last Order: Jan 10"
      }
    ]
  },
  "id": 123
}

​
Tool Whitelisting

Optionally restrict which tools your agent can access:
  1. In MCP server settings, expand Advanced Options
  2. Add tool names to the Tools Whitelist
  3. Only listed tools will be available to agents
Leave the whitelist empty to allow access to all tools from the server.

​
Agent Integration

Your AI agent automatically uses MCP tools when appropriate. To help the agent know when to use tools, update your agent’s description: 
You have access to these tools:
- get_customer: Use when you need customer information
- check_order_status: Use when customer asks about an order
- schedule_callback: Use to book follow-up calls

Always greet the customer, then use get_customer to look up their account.
The AI automatically speaks tool results to the customer in a natural way. You don’t need to script how results are presented.

​
Testing MCP

​
Test Server Connection

  1. Go to Dashboard → Integrations → MCP Servers
  2. Click Test on your server
  3. View discovered tools and verify they’re correct

​
Make a Test Call

  1. Go to Dashboard → Call Logs
  2. Click Test Call
  3. Select a campaign with MCP enabled
  4. Call yourself and test tool usage

​
MCP Configuration Options

SettingDescriptionDefault
URLYour MCP server’s SSE endpointRequired
API KeyAuthentication token (sent as Bearer)Optional
Tools WhitelistRestrict available toolsEmpty (all tools)
TimeoutMax time for tool execution5000ms

​
Best Practices

Fast Responses: Tools should respond within 5 seconds. Long operations cause awkward pauses in conversation.
Clear Descriptions: Write clear tool descriptions so the AI knows when to use each tool.
Handle Errors Gracefully: Return helpful error messages the AI can communicate to the customer.
Test Thoroughly: Make test calls to verify tools work correctly in real conversations.
Sensitive Data: Be careful with tools that return sensitive information. The AI may speak this to the customer.

​
Common Use Cases

Use CaseTools to Implement
Customer Lookupget_customer_by_phone
Order Statuscheck_order_status, track_shipment
Appointment Bookingget_available_slots, book_appointment
CRM Updatesupdate_contact, add_note
Knowledge Basesearch_faq, get_article

​
Example: CRM Integration

A typical CRM MCP server might provide:
ToolDescription
get_customerLook up customer by phone
get_recent_ordersList customer’s recent orders
update_statusUpdate customer status (lead → prospect)
add_noteAdd note to customer record
During a call:
  1. Call starts, agent greets customer
  2. Agent calls get_customer to retrieve their info
  3. Agent personalizes conversation based on customer data
  4. Customer asks about an order, agent calls get_recent_orders
  5. Call ends, agent calls add_note with call summary

​
Troubleshooting

​
Tools Not Discovered

  1. Verify server URL is correct (must be SSE endpoint)
  2. Check server is running and accessible
  3. Test the server directly using Preview
  4. Review server logs for connection issues

​
Tool Execution Failures

  1. Check timeout settings (increase if tools are slow)
  2. Review tool error messages in call logs
  3. Verify tool parameters match the schema
  4. Test tools individually using your MCP server’s interface

​
Agent Not Using Tools

  1. Update agent description to explain when to use tools
  2. Verify MCP is enabled on the campaign
  3. Check that tool descriptions are clear
  4. Make test calls to observe agent behavior

​
Build Your Own MCP Server

Don’t have an existing MCP server? Build your own using automation platforms like n8n, Zapier, or Make. This gives you the freedom to connect your AI agents to any tool or data source.

n8n

Build MCP endpoints visually

Any API

Connect to any REST API

Your Database

Query your own data
With a custom MCP server you can:
  • Look up customer data from your CRM
  • Check inventory or order status
  • Query your internal databases
  • Access any API during calls
  • Build custom tools specific to your business

Automation Workflows Guide

Learn how to build custom MCP servers with n8n and other tools

​
Next Steps

Configure Webhooks

Send call events to external systems

Set Up Agents

Configure your AI agent to use MCP tools