Skip to content
Workflows

Connect External MCP Servers to AI Agents in Workflows

Learn how to connect external MCP servers to AI Agents in GHL Customer Care Workflows for real-time searches, automation, and external tool access.

4 min read961 words5 explained images
View as markdownOpen in ClaudeOpen in ChatGPT
Each image has a one line explanation. Switch to full detail for the step it belongs to, the fields and buttons involved, examples and the whole procedure.
On this page
  1. Key Benefits of MCP Connections
  2. Supported MCP Servers
  3. Authentication Options
  4. Supported Transport Types
  5. How Tool Discovery Works
  6. Configure an MCP Connection
  7. Managing Tool Permissions
  8. Best Practices
  9. Frequently Asked Questions
  10. Related Articles

AI Agents in GHL Customer Care Workflows can now connect to external services using the Model Context Protocol (MCP). This allows your AI Agent to access real-time information from compatible tools such as web search providers, browser automation platforms, databases, and custom APIs. By extending your AI Agent beyond CRM data, you can automate research, enrich records, and perform more intelligent workflow actions.

TABLE OF CONTENTS

What are MCP Connections for AI Agents?

Model Context Protocol (MCP) is an open standard that enables AI applications to securely communicate with external tools and services. With MCP Connections in GHL Customer Care Workflows, AI Agents can connect to compatible MCP servers and use their available tools while executing workflow actions.

Unlike standard AI Agent capabilities that rely primarily on information available within GHL Customer Care, MCP Connections allow agents to retrieve live information, automate browser tasks, perform searches, and interact with external systems in real time.

Key Benefits of MCP Connections

Connecting external MCP servers expands what your AI Agent can accomplish during workflow execution.

  • Real-Time Data Access: Retrieve current information from external services while the workflow is running.
  • Extensible AI Capabilities: Connect to any compatible MCP server instead of being limited to built-in tools.
  • Automatic Tool Discovery: Detect available tools automatically after testing a connection.
  • Granular Tool Permissions: Choose exactly which tools each AI Agent is allowed to use.
  • Workflow Automation: Eliminate manual research and repetitive tasks by allowing AI Agents to interact with external services.
  • Flexible Authentication: Support multiple authentication methods depending on the MCP provider.

Supported MCP Servers

GHL Customer Care supports connections to any MCP-compatible server.

Common examples include:

  • Exa – AI-powered web search across companies, people, and news.
  • Tavily – Real-time web search and webpage extraction.
  • Browserbase – Browser automation for navigation, clicks, screenshots, and data extraction.
  • Custom MCP Servers – Self-hosted or internally developed MCP servers that follow the MCP specification.
Note: GHL Customer Care does not host or manage third-party MCP servers. Availability, pricing, authentication requirements, and supported tools are determined by the provider.

Authentication Options

Different MCP providers require different authentication methods. GHL Customer Care supports multiple authentication types to accommodate a variety of services.

Supported authentication methods include:

  • None
  • API Key
  • Bearer Token
  • OAuth2
  • Custom Header

Some providers allow API keys to be passed through HTTP headers, while others require them as query parameters. Refer to your MCP provider's documentation for the correct configuration.

Supported Transport Types

Transport types determine how GHL Customer Care communicates with the MCP server.

Supported transport options include:

  • HTTP Streamable (default)
  • Server-Sent Events (SSE)

Unless your provider specifies otherwise, use HTTP Streamable, which is the recommended default option.

How Tool Discovery Works

After entering your connection information, GHL Customer Care can validate the connection and retrieve the tools made available by the MCP server.

Selecting Test Connection will:

  • Verify communication with the server.
  • Validate authentication credentials.
  • Discover available tools automatically.
  • Display every tool returned by the MCP server.

After discovery, choose which tools your AI Agent can access.

Configure an MCP Connection

Proper configuration ensures your AI Agent can securely communicate with external services during workflow execution.

  1. Open the desired Workflow.
  2. Add or edit an AI Agent action.
  3. Select Add Tools.
    Step 3 of 10: Select Add Tools What this shows Step 3 of 10: Select Add Tools. What this shows Shows what to choose for step 3 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". This screenshot accompanies step 3 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". At this point in the walkthrough you select Add Tools. For context, this section explains: Proper configuration ensures your AI Agent can securely communicate with external services during workflow execution. The next step is to open the MCP tab. Step 3 of 10Image 1 of 5 What to chooseSelect Add Tools. Next stepOpen the MCP tab.
    All 10 steps in this procedure
    1. Open the desired Workflow.
    2. Add or edit an AI Agent action.
    3. Select Add Tools. this image
    4. Open the MCP tab.
    5. Click Add Connection.
    6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    7. Click Test Connection.
    8. Review the discovered tools.
    9. Enable only the tools the AI Agent should be allowed to use.
    10. Save the connection.
  4. Open the MCP tab.
    Step 4 of 10: Open the MCP tab What this shows Step 4 of 10: Open the MCP tab. What this shows Shows where to go for step 4 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". This screenshot accompanies step 4 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". At this point in the walkthrough you open the MCP tab. For context, this section explains: Proper configuration ensures your AI Agent can securely communicate with external services during workflow execution. The next step is to click Add Connection. Step 4 of 10Image 2 of 5 Where to goOpen the MCP tab. Next stepClick Add Connection.
    All 10 steps in this procedure
    1. Open the desired Workflow.
    2. Add or edit an AI Agent action.
    3. Select Add Tools.
    4. Open the MCP tab. this image
    5. Click Add Connection.
    6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    7. Click Test Connection.
    8. Review the discovered tools.
    9. Enable only the tools the AI Agent should be allowed to use.
    10. Save the connection.
  5. Click Add Connection.
    Step 5 of 10: Click Add Connection What this shows Step 5 of 10: Click Add Connection. What this shows Shows what to click for step 5 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". This screenshot accompanies step 5 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". At this point in the walkthrough you click Add Connection. For context, this section explains: Proper configuration ensures your AI Agent can securely communicate with external services during workflow execution. The next step is to enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials. Step 5 of 10Image 3 of 5 What to clickClick Add Connection. Next stepEnter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    All 10 steps in this procedure
    1. Open the desired Workflow.
    2. Add or edit an AI Agent action.
    3. Select Add Tools.
    4. Open the MCP tab.
    5. Click Add Connection. this image
    6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    7. Click Test Connection.
    8. Review the discovered tools.
    9. Enable only the tools the AI Agent should be allowed to use.
    10. Save the connection.
  6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    Step 6 of 10: Enter a descriptive Connection Name. Enter the Server URL supplied by… What this shows Step 6 of 10: Enter a descriptive Connection Name. What this shows Shows what to fill in for step 6 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". This screenshot accompanies step 6 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". At this point in the walkthrough you enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials. The next step is to click Test Connection. Step 6 of 10Image 4 of 5 What to fill inEnter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials. Next stepClick Test Connection.
    All 10 steps in this procedure
    1. Open the desired Workflow.
    2. Add or edit an AI Agent action.
    3. Select Add Tools.
    4. Open the MCP tab.
    5. Click Add Connection.
    6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials. this image
    7. Click Test Connection.
    8. Review the discovered tools.
    9. Enable only the tools the AI Agent should be allowed to use.
    10. Save the connection.
  7. Click Test Connection.
    Step 7 of 10: Click Test Connection What this shows Step 7 of 10: Click Test Connection. What this shows Shows what to click for step 7 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". This screenshot accompanies step 7 of 10 in the "Configure an MCP Connection" section of "Connect External MCP Servers to AI Agents in Workflows". At this point in the walkthrough you click Test Connection. For context, this section explains: Proper configuration ensures your AI Agent can securely communicate with external services during workflow execution. The next step is to review the discovered tools. Step 7 of 10Image 5 of 5 What to clickClick Test Connection. Next stepReview the discovered tools.
    All 10 steps in this procedure
    1. Open the desired Workflow.
    2. Add or edit an AI Agent action.
    3. Select Add Tools.
    4. Open the MCP tab.
    5. Click Add Connection.
    6. Enter a descriptive Connection Name. Enter the Server URL supplied by your MCP provider. Select the appropriate Transport Type. Choose the required Authentication Type. Enter any required credentials.
    7. Click Test Connection. this image
    8. Review the discovered tools.
    9. Enable only the tools the AI Agent should be allowed to use.
    10. Save the connection.
  8. Review the discovered tools.
  9. Enable only the tools the AI Agent should be allowed to use.
  10. Save the connection.

Managing Tool Permissions

Each MCP server may expose multiple tools. Not every workflow requires access to every available capability.

Limiting tool access helps improve security, simplifies AI decision-making, and ensures the agent only performs approved actions.

After testing the connection:

  • Review the discovered tools.
  • Enable only the required tools.
  • Disable tools that are unnecessary for the workflow.
  • Save your selections.

These permissions apply at the AI Agent level, allowing different agents to use different tool sets even when connecting to the same server.

Best Practices

Following these recommendations helps improve reliability and security when using external MCP services.

  • Connect only trusted MCP providers.
  • Use descriptive names for each connection.
  • Enable only the tools required by the workflow.
  • Test every connection before activating production workflows.
  • Rotate API credentials according to your organization's security policies.
  • Monitor third-party service availability.
  • Review tool permissions periodically as workflows evolve.

Frequently Asked Questions

Q: What is an MCP server?
A: An MCP server exposes tools that AI applications can use through the Model Context Protocol.

Q: Can I connect more than one MCP server to an AI Agent?
A: If supported by the AI Agent configuration, multiple MCP connections can be added, allowing the agent to use tools from different providers.

Q: Does GHL Customer Care provide MCP servers?
A: No. GHL Customer Care provides the ability to connect to compatible MCP servers. Third-party providers or your organization are responsible for hosting and managing those servers.

Q: What happens if the Test Connection fails?
A: Verify the server URL, authentication settings, API credentials, transport type, and that the MCP server is online and reachable.

Q: Can I restrict which tools an AI Agent uses?
A: Yes. After tool discovery, you can enable or disable individual tools before saving the connection.

Q: Are third-party MCP services included with my GHL Customer Care subscription?
A: No. Third-party providers may require their own accounts, subscriptions, or API usage fees.

Was this guide helpful?

Related guides

Triggers - Overview1 min read · 1 imagesWorkflow Trigger - Exact Match & Contains Phrase1 min readHow to Create A Task Event and Task Reminder in Campaigns1 min readHow To Send New Membership Users Custom Emails With Their Login Information6 min read · 20 images