The Freshdesk connector.
Tickets, conversations, contacts and agents. Connect once with your own key. Every agent your team runs reads the same 6 tools under one permission model.
How access is governed
6
Read tools
Open by default. They run when called, and every call is logged with the endpoint, tool and capability.
0
Write tools
Freshdesk exposes no write tools. Nothing it does mutates external state.
0
Destructive tools
Freshdesk defines no destructive tools. Nothing here deletes data.
Defaults come from the capability on each tool definition, and an admin can tighten or open any tool individually. The endpoint's capability ceiling can only tighten that policy. An endpoint scoped to read never surfaces a write tool.
Every Freshdesk tool
6 tools, named as the agent sees them.
- list_ticketsread
List recent tickets, newest activity first. Good for "what is in the queue right now". Returns ticket ids that get_ticket and list_ticket_conversations take. For anything conditional (a status, a priority, a tag) use search_tickets instead.
- search_ticketsread
Filter tickets with the Freshdesk query language, e.g. 'status:2 AND priority:4' or 'tag:\'billing\' AND created_at:>\'2026-01-01\''. Status is 2 Open / 3 Pending / 4 Resolved / 5 Closed; priority is 1 Low / 2 Medium / 3 High / 4 Urgent. Returns ticket ids for get_ticket.
- get_ticketread
Get one ticket with its opening description as plain text. Takes an id from list_tickets or search_tickets. Read the replies with list_ticket_conversations.
- list_ticket_conversationsread
List a ticket's replies and notes as plain text, oldest first. `private: true` marks an internal note the customer never saw; `incoming: true` means it came from the customer. `user_id` resolves through list_contacts or list_agents.
- list_contactsread
List customer contacts. Use it to turn the requester_id / user_id numbers on tickets into names and emails, or to look a customer up by email before searching their tickets.
- list_agentsread
List support agents. Use it to resolve the responder_id on a ticket, or to see who is currently available before routing work.
Use it from any agent
The same Freshdesk tools reach Claude Code, Cursor, Claude Desktop or your own agent through one MCP endpoint. The endpoint is scoped to a group, the token is issued per group and revocable from the dashboard, and an allowed-tool list and capability ceiling limit what it exposes. Reads run. Gated writes refuse unless an admin opens them. Destructive tools remain unavailable over MCP.
{
"mcpServers": {
"growth": {
"type": "http",
"url": "https://app.notara.ai/mcp/g/acme/growth",
"headers": {
"Authorization": "Bearer ntr_mcp_xxxxxxxxxxxxxxxxxxxx"
}
}
}
}The URL and token are placeholders. Real endpoints are issued per group from the dashboard.
Setup
- 01
Create a Freshdesk API Key in your Freshdesk account (where to find it). The key is yours: Notara stores it encrypted and never sees a bill.
- 02
Paste it into the Notara dashboard. Credentials can be scoped to the workspace or to one person.
- 03
The tools appear with their capability defaults already set. Tighten or open any of them per tool, then invite the agent to a channel or issue an MCP token.
Connect Freshdesk once. Use it everywhere.
Use Notara directly, or bring us the workflow that needs to be redesigned and built.