Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Freshdesk MCP Server show me all open high priority tickets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Hey! This is a custom Model Context Protocol (MCP) server for Freshdesk. It's built on top of FastMCP to let your AI agents (like Claude Desktop or custom LangChain setups) read and write directly to your Freshdesk account.
I've packed in a bunch of tools so the AI can handle almost any helpdesk task:
Tickets & Responses
get_tickets: Search and filter incoming tickets.
get_ticket: Pull all details for a specific ticket.
create_ticket: Open a new support ticket.
update_ticket: Change status or priority.
delete_ticket: Trash a ticket (be careful with this one).
reply_ticket: Send a reply to the customer.
add_note: Drop an internal or public note on a thread.
list_conversations: Grab the entire back-and-forth history of a ticket.
create_outbound_email: Send proactive emails (fully supports CC, BCC, tags, and custom fields).
Customers & Companies
search_contacts: Look up customers by email or phone.
get_contact / create_contact / update_contact: Manage your user base.
get_company / create_company: Manage companies.
Agents & Knowledge Base
list_agents / get_agent: See who is working on what.
search_solution_articles / get_solution_article: Let the AI search your help docs so it can answer questions better.
Related MCP server: Freshservice MCP Server
If you just want to run this locally on your own machine (like inside Claude Desktop), it's super simple:
Clone this repo and set up your environment:
python -m venv venv
source venv/bin/activate
pip install -e .Copy the .env.example file to .env and drop in your Freshdesk domain and API key.
Start it up:
mcp dev src/freshdesk_mcp/server.pyIf you're hosting this on a cloud server so multiple remote agents can talk to it, you don't want just anyone hitting your API. I built a lightweight, database-free JWT authentication layer over the SSE connection to keep it safe.
Here's how to use it:
In your .env, set up your JWT_SECRET_KEY and define who is allowed to connect using ALLOWED_CLIENTS=agent1:pass123,agent2:secure456.
Run the secure server wrapper:
python -m freshdesk_mcp.serveYour clients will first need to send a POST request to /token (using Basic Auth with their agent credentials) to get a 1-hour JWT.
They can then connect to the main MCP stream by passing Authorization: Bearer <their_token> in the headers.
(Pro-tip: If you want to make sure an AI agent can only read data and doesn't accidentally delete anything, just set STRICT_MODE=True in your .env and it will lock down all destructive tools).
MIT License - feel free to use and modify it however you need!
Add a note to a ticket. private=True means it is an internal note.
Inputs: body (required), ticket_id (required), private. Returns: result
Create a new company.
Inputs: name (required), description. Returns: result
Create a new customer contact.
Inputs: name (required), email (required), phone. Returns: result
Create and send an outbound email from Freshdesk. Supports cc, bcc, tags, and custom fields.
Inputs: email (required), subject (required), description (required), email_config_id (required), +7 more. Returns: result
Create a new Freshdesk ticket. Priority: 1=Low, 2=Medium, 3=High, 4=Urgent. Status: 2=Open, 3=Pending, 4=Resolved, 5=Closed.
Inputs: email (required), subject (required), description (required), status, +1 more. Returns: result
Delete a specific ticket.
Inputs: ticket_id (required). Returns: result
Get specific agent details by ID.
Inputs: agent_id (required). Returns: result
Retrieve company details by ID.
Inputs: company_id (required). Returns: result
Retrieve contact details by ID.
Inputs: contact_id (required). Returns: result
Retrieve the content of a specific knowledge base article.
Inputs: article_id (required). Returns: result
Get detailed information about a specific ticket by ID.
Inputs: ticket_id (required). Returns: result
List tickets in Freshdesk. Optionally filter by requester email.
Inputs: page, email. Returns: result
List support agents. Optionally filter by email.
Inputs: email. Returns: result
Fetch all replies and notes associated with a ticket.
Inputs: ticket_id (required). Returns: result
Reply to an existing ticket.
Inputs: body (required), ticket_id (required). Returns: result
Find a contact by email, phone, or mobile.
Inputs: email, phone, mobile. Returns: result
Search for knowledge base articles by keyword.
Inputs: keyword (required). Returns: result
Update an existing contact's details.
Inputs: contact_id (required), name, email, phone. Returns: result
Update a ticket's status or priority.
Inputs: ticket_id (required), status, priority. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 19 tools
Each tool targets a distinct resource and action. While add_note, reply_ticket, and create_outbound_email all relate to ticket communication, their purposes are clearly separated: notes, replies, and outbound emails respectively. No two tools could be easily confused.
All tool names follow a consistent verb_noun pattern in snake_case, such as create_ticket, get_contact, list_agents. The verbs are consistently chosen (create, get, list, update, delete, search, reply, add) and the nouns are singular or plural as appropriate.
With 19 tools, the server is slightly above the ideal range of 3-15, but each tool serves a distinct and necessary function within the Freshdesk domain. The count is justifiable given the variety of entities (tickets, contacts, companies, agents, knowledge base) and operations.
The tool set provides comprehensive coverage for tickets (CRUD, notes, replies, conversations, outbound emails). Contacts and companies have create, read, and update operations but lack delete and listing capabilities. Knowledge base supports search and retrieval but not curation. Overall, core workflows are well-supported with minor gaps.
Search, reply, tag, assign and report on ThriveDesk help desk conversations from your AI assistant.
Work your HelpRabbit help desk: tickets, replies, customers, the AI agent and its knowledge.
Manage tickets, run agents and workflows, query tables, and search workspace knowledge.
Work your miniDesk support inbox from AI apps: read conversations, search docs, draft replies.