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.
README
Freshservice MCP Server
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
uvxinstalled (pip install uvorbrew install uv)
Configuration
-
Generate your Freshservice API key from the admin panel:
- Navigate to Profile Settings → API Settings
- Copy your API key for configuration
-
Set up your domain and authentication details as shown below
Usage with Claude Desktop
- Install Claude Desktop from the official website
- 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
uvxcommand 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
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.