
Get a specific Freshdesk agent by ID
Get the currently authenticated Freshdesk agent
List all Freshdesk agents with optional filtering by email, phone, or state
Update a Freshdesk agent's signature, ticket scope, groups, or roles
Get a specific Freshdesk company by ID
List all Freshdesk companies with pagination
Create a new Freshdesk company with name, domains, and other details
Update an existing Freshdesk company's name, domains, or other details
Delete a Freshdesk company by ID
Search Freshdesk companies using query string. Supported fields: domain, custom_fields
Get a specific Freshdesk contact by ID
List Freshdesk contacts with optional filtering by email, phone, company, or state
Create a new Freshdesk contact with name, email, phone, and other details
Update an existing Freshdesk contact's name, email, phone, or other details
Delete a Freshdesk contact by ID (soft delete)
Search Freshdesk contacts using query string with filters like email, name, or company_id
List all conversations (notes and replies) for a Freshdesk ticket
Add a private or public note to a Freshdesk ticket
Add a reply to a Freshdesk ticket that is sent to the requester
Get a specific Freshdesk group by ID
List all Freshdesk groups with pagination
Create a new Freshdesk group with name, agents, and escalation settings
Update an existing Freshdesk group's name, agents, or escalation settings
Delete a Freshdesk group by ID
Get a specific Freshdesk ticket by ID with optional includes for conversations, requester, company, or stats
List Freshdesk tickets with optional filtering by requester, email, company, status, or date
Create a new Freshdesk ticket with subject, description, requester email, priority, and status
Update an existing Freshdesk ticket's subject, description, status, priority, or assignment
Delete a Freshdesk ticket by ID
Search Freshdesk tickets using query string with filters like status, priority, or created_at
Validate Freshdesk credentials. Verifies credentials during setup.

In an mcp.json file, add the configuration below, and restart Cursor.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5 "headers": {
6 "Authorization": "Bearer yMt*****"
7 }
8 }
9 }
10}
11Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.
Make sure Claude is using the Node v20+.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "yMt*****"
14 }
15 }
16 }
17}Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.
Learn more in the official documentation ↗
1{
2 "mcpServers": {
3 "agent-handler": {
4 "command": "npx",
5 "args": [
6 "-y",
7 "mcp-remote@latest",
8 "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9 "--header",
10 "Authorization: Bearer ${AUTH_TOKEN}"
11 ],
12 "env": {
13 "AUTH_TOKEN": "<ah-production-access-key>"
14 }
15 }
16 }
17 }In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".
You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.
Learn more in the official documentation ↗
1{
2 "inputs": [
3 {
4 "type": "promptString",
5 "id": "agent-handler-auth",
6 "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7 "password": true
8 }
9 ],
10 "servers": {
11 "agent-handler": {
12 "type": "stdio",
13 "command": "npx",
14 "args": [
15 "-y",
16 "mcp-remote@latest",
17 "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18 "--header",
19 "Authorization: Bearer ${input:agent-handler-auth}"
20 ]
21 }
22 }
23}It’s an MCP server that exposes data and functionality from Freshdesk via tools. Your agents can use these tools to edit contacts, update a company’s information, provide a list of Freshdesk agents, and more.
Since Freshdesk doesn’t currently offer an official MCP server, it’s provided by 3rd-party platforms, like Merge Agent Handler.
Here are some examples (these apply to any project management MCP servers):
Merge Agent Handler provides the following advantages for its Freshdesk MCP server:
Yes. Merge Agent Handler includes a Security Gateway with Data Loss Protection (DLP) that allows you to define custom rules for tool inputs and outputs, such as blocking or redacting sensitive fields. These rules apply to all connectors, including Freshdesk.
Here are a few rules you can add:
You can take the following steps:
1. Create a free Agent Handler account and log in.
2. Add the Freshdesk connector to a Tool Pack. Create a Tool Pack for your use case (for example, “Support Triage”), then include Freshdesk and select only the Freshdesk tools you want the agent to be able to call.
3. Create (or select) a Registered User for the end user. Registered users act as the per-user container that tool calls run “on behalf of”.
4. Have the end user link their Freshdesk account. When a Freshdesk tool call requires auth, Agent Handler prompts for credentials so the user links Freshdesk with the right permissions.
5. Use the Agent Handler MCP server for that Tool Pack + Registered User. Your agent runtime connects to the MCP server associated with the Tool Pack and Registered User, then can list and call the Freshdesk tools you enabled.
6. You can set security rules for Freshdesk tool calls. This includes turning on prebuilt rules and adding custom rules (block, redact, or log) that scan Freshdesk tool inputs/outputs for sensitive data.
7. Validate everything via logs. After you start making Freshdesk tool calls, confirm the request/response behavior and any security events in the logs/audit trail.
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Freshdesk without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity.
IT also provisions access by role or group via SCIM. A support agent, for instance, gets Freshdesk access to manage and resolve tickets, Jira to track escalated bugs, and Slack to coordinate with engineering; while a team lead gets Freshdesk to monitor queue health, Salesforce to review account context for escalations, and Google Sheets to track team performance.
Every tool call an employee's AI makes to Freshdesk is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.
Whether you're an engineer experimenting with agents or a product manager looking to add tools, you can get started for free now