Freshservice MCP Server

Freshservice MCP Server

Enables AI models to interact with Freshservice IT service management platform, allowing automated ticket management, change requests, asset tracking, and solution article operations through natural language commands.

Category
Visit Server

README

Freshservice MCP Server

smithery badge

Overview

A powerful MCP (Model Context Protocol) server implementation that seamlessly integrates with Freshservice, enabling AI models to interact with Freshservice modules and perform various IT service management operations. This integration bridge empowers your AI assistants to manage and resolve IT service tickets, streamlining your support workflow.

Key Features

  • Enterprise-Grade Freshservice Integration: Direct, secure communication with Freshservice API endpoints
  • AI Model Compatibility: Enables Claude and other AI models to execute service desk operations through Freshservice
  • Automated ITSM Management: Efficiently handle ticket creation, updates, responses, and asset management
  • Workflow Acceleration: Reduce manual intervention in routine IT service tasks

Supported Freshservice Modules

This MCP server currently supports operations across a wide range of Freshservice modules:

  • Tickets
  • Changes
  • Conversations
  • Products
  • Requesters
  • Agents
  • Agent Groups
  • Requester Groups
  • Canned Responses
  • Canned Response Folders
  • Workspaces
  • Solution Categories
  • Solution Folders
  • Solution Articles

Components & Tools

The server provides a comprehensive toolkit for Freshservice operations:

Ticket Management

Tool Description Key Parameters
create_ticket Create new service tickets subject, description, source, priority, status, email
update_ticket Update existing tickets ticket_id, updates
delete_ticket Remove tickets ticket_id
filter_tickets Find tickets matching criteria query
get_ticket_fields Retrieve ticket field definitions None
get_tickets List all tickets with pagination page, per_page
get_ticket_by_id Retrieve single ticket details ticket_id

Change Management

Tool Description Key Parameters
get_changes List all changes with pagination page, per_page, query
filter_changes Filter changes with advanced queries query, page, per_page
get_change_by_id Retrieve single change details change_id
create_change Create new change request requester_id, subject, description, priority, impact, status, risk, change_type
update_change Update existing change change_id, change_fields
close_change Close change with result explanation change_id, change_result_explanation
delete_change Remove change change_id
get_change_tasks Get tasks for a change change_id
create_change_note Add note to change change_id, body

🚨 Important: Query Syntax for Filtering

When using get_changes or filter_changes with the query parameter, the query string must be wrapped in double quotes for the Freshservice API to work correctly:

CORRECT: "status:3", "approval_status:1 AND status:<6"
WRONG: status:3 (will cause 500 Internal Server Error)

Common Query Examples:

  • "status:3" - Changes awaiting approval
  • "approval_status:1" - Approved changes
  • "approval_status:1 AND status:<6" - Approved changes that are not closed
  • "planned_start_date:>'2025-07-14'" - Changes starting after specific date
  • "status:3 AND priority:1" - High priority changes awaiting approval

Getting Started

Installing via Smithery

To install freshservice_mcp automatically via Smithery:

npx -y @smithery/cli install @effytech/freshservice_mcp --client claude

Prerequisites

  • A Freshservice account (sign up at freshservice.com)
  • Freshservice API key
  • uvx installed (pip install uv or brew install uv)

Configuration

  1. Generate your Freshservice API key from the admin panel:

    • Navigate to Profile Settings → API Settings
    • Copy your API key for configuration
  2. Set up your domain and authentication details as shown below

Usage with Claude Desktop

  1. Install Claude Desktop from the official website
  2. Add the following configuration to your claude_desktop_config.json:
"mcpServers": {
  "freshservice-mcp": {
    "command": "uvx",
    "args": [
        "freshservice-mcp"
    ],
    "env": {
      "FRESHSERVICE_APIKEY": "<YOUR_FRESHSERVICE_APIKEY>",
      "FRESHSERVICE_DOMAIN": "<YOUR_FRESHSERVICE_DOMAIN>"
    }
  }
}

Important: Replace <YOUR_FRESHSERVICE_APIKEY> with your actual API key and <YOUR_FRESHSERVICE_DOMAIN> with your domain (e.g., yourcompany.freshservice.com)

Example Operations

Once configured, you can ask Claude to perform operations like:

Tickets:

  • "Create a new incident ticket with subject 'Network connectivity issue in Marketing department' and description 'Users unable to connect to Wi-Fi in Marketing area', set priority to high"
  • "List all critical incidents reported in the last 24 hours"
  • "Update ticket #12345 status to resolved"

Changes:

  • "Create a change request for scheduled server maintenance next Tuesday at 2 AM"
  • "Update the status of change request #45678 to 'Approved'"
  • "Close change #5092 with result explanation 'Successfully deployed to production. All tests passed.'"
  • "List all pending changes"

Other Operations:

  • "Show asset details for laptop with asset tag 'LT-2023-087'"
  • "Create a solution article about password reset procedures"

Testing

For testing purposes, you can start the server manually:

uvx freshservice-mcp --env FRESHSERVICE_APIKEY=<your_api_key> --env FRESHSERVICE_DOMAIN=<your_domain>

Troubleshooting

  • Verify your Freshservice API key and domain are correct
  • Ensure proper network connectivity to Freshservice servers
  • Check API rate limits and quotas
  • Verify the uvx command is available in your PATH

License

This MCP server is licensed under the MIT License. See the LICENSE file in the project repository for full details.

Additional Resources


<p align="center">Built with ❤️ by effy</p>

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured