The Freshworks Model Context Protocol (MCP) server enables AI tools like Cursor and Claude to securely connect and interact with Freshdesk. The MCP server acts as middleware to expose specific capabilities, such as creating tickets, by using public APIs and supported authentication methods. 

This article provides details about supported MCP integrations and how to configure them in your AI tools.

TABLE OF CONTENTS


Note: Currently, Freshdesk allows you to authenticate requests involved in MCP integration by using an API key only.


Supported plans and limits

Applicable plans: Freshdesk Enterprise

Important: Freshworks MCP integration is currently in Beta and available through an Early Access Program (EAP) for selected customers on the Enterprise plan. To request access to this feature, contact your technical account manager or email the support team at support@freshdesk.com.


Access requirements: MCP integration in Freshdesk is accessible only to users with administrator and agent privileges.

Integration limits: The following limits apply during the early access period. These limits are subject to change and may incur charges after general availability.


Plan


Tool calls per minute

Tool calls (actions) per month


Tool Permissions


Enterprise

100

 5,000

Full tool access 


Supported MCP integrations

Freshdesk currently supports MCP integration for the following AI tools:

Set up MCP integration with Claude Code

Connect and verify the MCP server within the Claude Code editor. After the setup is complete, Claude Code can use tools exposed by the MCP server directly within the editor.

Prerequisites

Before you begin, ensure you have the following:

  • The Claude Code app installed.

  • An active Claude account.

  • The Freshdesk MCP URL.

Create an MCP connection

To connect Claude Code to your MCP server, you must register the server using the http transport.

Run the following command in your terminal to register the Freshdesk MCP server:

claude mcp add my-remote-server --transport http https://<your-freshdesk-domain>/mcp  --header "Authorization: <api-key>"


Expected output:

Added HTTP MCP server my-remote-server with URL: https://<your-freshdesk-domain>/mcp to local config

Headers: {

  "Authorization": "<api-key>"

}

File modified: /Users/<username>/.claude.json [project: /Users/pmm]


Verify the connection

Use the following get command to confirm the server is listed as connected within the application:

claude mcp get my-remote-server

Expected output:


my-remote-server:

  Scope: Local config (private to you in this project)

  Status: ✓ Connected

  Type: http

  URL: https://<domain>/mcp

  Headers:

    Authorization: <api-key>



Set up MCP integration with Claude Desktop

Connect and verify the MCP server within the Claude Desktop editor. After the setup is complete, Claude Desktop can use tools exposed by the MCP server directly within the editor.

Prerequisites

Before you begin, ensure you have the following:

  • The Claude Desktop app installed.

  • An active Claude account.

  • The Freshdesk MCP URL.

Create an MCP connection

To connect Claude Desktop to your MCP server, follow these steps:

  1. Open Claude Desktop and go to Claude > Settings > Developer.

  2. Select Edit Config. The claude_desktop_config.json file opens in your system's default text editor.

  3. Copy and paste the following JSON configuration into the file. If other servers are already listed, add this as a new entry in the mcpServers object.

    Note: Replace <mcp-url> with your specific server URL (for example, https://<your-freshdesk-domain>/mcp).

   "mcpServers": {

   "freshdesk-mcp": {

     "command": "npx",

     "args": [

       "-y",

       "mcp-remote",

       "https://<your-freshdesk-domain>/mcp",

       "--header",

       "Authorization:<API_KEY>"

     ]

   }

  }

  1. Save the file and close the text editor.

  2. Exit Claude Desktop by right-clicking the icon in the taskbar (Windows) or menu bar (macOS) and selecting Quit.

  3. Relaunch Claude Desktop.
  4. Follow the authentication prompts in your browser. After successful authentication, you can verify the connection status under Claude > Settings > Developer.



Set up MCP integration with Cursor

Connect and verify the MCP server within the Cursor editor. After the setup is complete, Cursor can use tools exposed by the MCP server directly within the editor.

Prerequisites

Before you begin, ensure you have the following:

  • The Cursor app installed.

  • An active Cursor account.

  • The Freshdesk MCP URL.

Create an MCP connection

To connect Cursor to the MCP server, add the server details to your application's configuration file. To do so, follow these steps:

  1. Open Cursor and go to the root folder of your project or user home directory for global configuration.

  2. Create or update the .cursor/mcp.json file.

  3. Add the following JSON object to the file:


    Sample configuration using API key

{

  "mcpServers": {

    "freshdesk": {

      "type": "http",

      "url": "https://<your-freshdesk-domain>/mcp",

      "headers": {

       "Authorization": "<API-KEY>"

      }

    }

  }

}


The following table describes the attributes used to configure the MCP server:


Attribute name

Description

mcpServers

List of all MCP servers to which the Cursor should connect.

Attribute of the mcpServers object

<name_of_the_MCP_object>

The unique name for your MCP server object.

Attribute of the <name_of_the_MCP_object> object

type

The protocol used by the MCP client to communicate with the MCP server.

url

The endpoint used by the MCP client to connect to your MCP server.

headers 

Custom HTTP headers that the MCP client must send when connecting to your MCP server.


Note: Freshdesk supports authorization via API key only. In your configuration, include the "Authorization": "<YOUR_API_KEY>" attribute and replace <YOUR_API_KEY> with your actual Freshdesk API key.


    

Verify the configuration

After you save the configuration file, follow these steps to verify that Cursor can access the server and its tools:

  1. In Cursor, go to View > Command Palette

  2. Enter View: Open MCP Settings and select it from the list.

  3. On the Tools page, locate the Installed MCP Servers section and verify your server name appears.

  4. To view the available tools, expand the server card.

Once the connection is established, Cursor automatically retrieves the tools. You can invoke them through natural language prompts or allow Cursor to suggest them based on your current task.

If the server is offline or the configuration is incorrect, Cursor displays an error message provided by the MCP server in the settings view.


Set up MCP integration with Microsoft Copilot Studio

Connect and verify the MCP server within the Microsoft Copilot Studio editor. After the setup is complete, Microsoft Copilot Studio can use tools exposed by the MCP server directly within the editor.

Prerequisites 

Before you begin, ensure you have the following:

  • The Microsoft Copilot Studio app installed.

  • An active Microsoft Copilot Studio account.

  • An existing agent created within Microsoft Copilot Studio.

  • The Freshdesk MCP URL.

Create an MCP connection

To link Copilot Studio to your MCP server, follow these steps:

  1. In the Copilot Studio dashboard, select Agents from the left navigation pane.

  2. Select your agent from the list.

  3. Open the Tools page for the agent.

  4. Click + Add a tool at the top left of the page.
    The     Add tool window appears.


  5. Select + New tool > Model Context Protocol.
    The     Add a Model Context Protocol server window appears.


  6. Enter the following details:

    • Server name: Enter a name for the server.

    • Server description: Provide a short description of why the server is required.

    • Server URL: Enter the endpoint where the MCP client can reach your MCP server. For example, https://<your-freshdesk-domain>/mcp.

    • Authentication: Select the authentication mode as API key

    • Click Create.
      After successful creation, the       Add tool window appears to configure the connection.

  7. In the Connection dropdown, you will see No connections available.
    Click the dropdown and select     Create new connection > Create.

  8. In the authorization window, select your account name and click Continue.

  9. After authorization succeeds, click Add and configure on the Add tool window.

You are redirected to the page for the newly created tool. Under the Tools section, you can view the list of available tools. 

Verify the MCP connection

To confirm that your agent is actively connected to the Freshworks MCP server, follow these steps:

  1. Go to your agent in Copilot Studio by selecting Agents and choosing the agent you want to verify.
    The agent overview page opens.

  2. Select Settings to open the agent settings page.

  3. In the left navigation pane, select Connection Settings.
    A table displays all connections associated with your agent.

  4. For the newly configured connection, if the status is Not connected, click Connect.
    The     Create or pick a connection window appears.

  5. Select the newly created connection and click Submit.

The status updates to Connected once the link is successfully established.


Set up MCP integration with Visual Studio Code

Connect and verify the MCP server within the Visual Studio Code editor . After the setup is complete, Visual Studio Code can use tools exposed by the MCP server directly within the editor.

Prerequisites

Before you begin, ensure you have the following:

  • The Visual Studio Code app installed.

  • The MCP extension for VS Code installed.

  • The Freshdesk MCP URL.

Create an MCP connection

To integrate the MCP server into your VS Code environment, follow these steps:

  1. Launch VS Code.

  2. Open the Command Palette by pressing Ctrl+Shift+P (Windows) or Cmd+Shift+P (macOS).

  3. Enter and select MCP: Open User Configuration.


  4. Add the following JSON object to the mcp.json file and save it.
    {

    "servers": {

        "my-remote-server": {

            "type": "http",

            "url": "https://<your-freshdesk-domain>/mcp",

            "headers": {

                "Authorization": "<api-key>"

            }

        }

    }

}

  1. A Start button appears above the my-remote-server entry. Click Start to initialize the server.

The following output appears to confirm the server is active:

Verify the configuration

After setting up your connection, you can confirm the server is running using either of the following methods:

  • View active servers: Open the Command Palette and select MCP: List Servers. Ensure your Freshdesk server is listed as active.

  • Review raw config: Open your mcp.json file to verify the server details and configuration target.

You can now run MCP-specific commands directly within your VS Code terminal or command palette to interact with Freshdesk data.


Troubleshoot issues

Issue: Connection failures

If the connection verification fails, check the following:

  • Network: Check your active internet connection and VPN status.

  • URL Accessibility: Open https://<domain>/mcp in your browser to ensure the endpoint is live.

  • Authentication: Verify that a valid API key is included in the authorization header.


List of available tools

The following table lists the tools provided by Freshworks MCP server for Freshdesk.

Resource

Tool

Description

Tickets

createTicket

Create a ticket

Tickets

fetchTicket

Get details of a particular ticket

Tickets

fetchTickets

Get list of tickets

Tickets

fetchSearchTickets

Filter tickets based on search criteria

Tickets

updateTicket

Update an existing ticket

Tickets

createTicketBulkUpdate

Update multiple tickets in bulk

Tickets

fetchTicketConversations

Get conversations associated with a ticket

Conversations

replyTicket

Reply to a ticket conversation

Conversations

createTicketNote

Add a note to a ticket

Conversations

updateConversation

Add a message to an existing conversation

Contacts

createContact

Create a contact

Contacts

fetchContact

Get details of a particular contact

Contacts

fetchContacts

Get list of contacts

Contacts

fetchContactAutocomplete

Search for a contact by name

Agents

fetchAgent

Get details of an agent

Agents

fetchAgents

Get list of agents

Agents

createAgent

Create an agent

Agents

updateAgent

Update an existing agent

Groups

createGroup

Create a group

Groups

fetchGroup

Get details of a particular group

Groups

fetchGroups

Get list of groups

Groups

updateGroup

Update details of a group

Companies

createCompany

Create a company

Companies

fetchCompany

Get details of a particular company

Companies

fetchCompanyAutocomplete

Search for a company by name

Companies

fetchSearchCompanies

Filter companies using custom company fields

Companies

updateCompany

Update an existing company

Solution Category

fetchSolutionCategories

Get list of solution categories

Solution Category

fetchSolutionCategory

Get details of a particular solution category

Solution Category

createSolutionCategory

Create a solution category

Solution Folder

fetchSolutionCategoryFolders

Get folders associated with a category

Solution Folder

fetchSolutionFolder

Get details of a particular solution folder

Solution Folder

createSolutionCategoryFolder

Create a solution folder.

Solution Article

fetchSolutionFolderArticles

Get articles associated with a folder

Solution Article

fetchSolutionArticle

Get details of a solution article

Solution Article

createSolutionFolderArticle

Create a solution article

Solution Article

updateSolutionArticle

Update a solution article


Pagination in MCP

When an MCP tool returns many results, such as a list of solution articles, sending the entire payload at once can exceed token limits or cause the LLM to truncate the data. Large payloads can also slow down response times and reduce the accuracy of the AI.

To prevent this, the MCP server uses pagination to deliver results in smaller, manageable batches. This ensures the LLM processes information efficiently while staying within its operational limits.

The pagination process provides the following benefits:

  • Automatic processing: The MCP client and the LLM handle subsequent data requests automatically using the nextCursor parameter.

  • No manual configuration: You don't need to manage page numbers, cursors, or page sizes manually.

  • Optimized performance: Smaller response batches ensure more reliable processing and faster response times from the AI tool.

Example prompts

You can use the following prompts to interact with the Freshdesk MCP server through your AI tool. These are samples only; you can modify them to suit your specific requirements.

  • Manage tickets:

    • "Create a high-priority ticket for a payment issue from Sarah."

    • "Get all tickets created today and group them by status."

    • "Filter my assigned tickets for those with 'open' status and 'high' priority."

  • Manage users and groups:

    • "Create a contact for John Doe with the email johndoe@acme-corp.com."

    • "Add a new support group called 'Network Team'."

    • "Show me the members of the Network Team group."

  • Manage companies and articles:

    • "Create a company named 'Acme Corp'."

    • "Find the solution article for payment refunds."