Freshdesk MCP Server
An MCP server implementation that integrates with Freshdesk, enabling AI models to interact with Freshdesk modules and perform various support operations.
README
Freshdesk MCP Server
An MCP server implementation that integrates with Freshdesk, enabling AI models to interact with Freshdesk modules and perform various support operations.
Features
- Freshdesk Integration: Seamless interaction with Freshdesk API endpoints
- AI Model Support: Enables AI models to perform support operations through Freshdesk
- Automated Ticket Management: Handle ticket creation, updates, and responses
Components
Tools
The server offers several tools for Freshdesk operations:
-
create_ticket: Create new support tickets- Inputs:
subject(string, required): Ticket subjectdescription(string, required): Ticket descriptionsource(number, required): Ticket source codepriority(number, required): Ticket priority levelstatus(number, required): Ticket status codeemail(string, optional): Email of the requesterrequester_id(number, optional): ID of the requestercustom_fields(object, optional): Custom fields to set on the ticketadditional_fields(object, optional): Additional top-level fields
- Inputs:
-
update_ticket: Update existing tickets- Inputs:
ticket_id(number, required): ID of the ticket to updateticket_fields(object, required): Fields to update
- Inputs:
-
delete_ticket: Delete a ticket- Inputs:
ticket_id(number, required): ID of the ticket to delete
- Inputs:
-
search_tickets: Search for tickets based on criteria- Inputs:
query(string, required): Search query string
- Inputs:
-
get_ticket_fields: Get all ticket fields- Inputs:
- None
- Inputs:
-
get_tickets: Get all tickets- Inputs:
page(number, optional): Page number to fetchper_page(number, optional): Number of tickets per page
- Inputs:
-
get_ticket: Get a single ticket- Inputs:
ticket_id(number, required): ID of the ticket to get
- Inputs:
-
get_ticket_conversation: Get conversation for a ticket- Inputs:
ticket_id(number, required): ID of the ticket
- Inputs:
-
create_ticket_reply: Reply to a ticket- Inputs:
ticket_id(number, required): ID of the ticketbody(string, required): Content of the reply
- Inputs:
-
create_ticket_note: Add a note to a ticket- Inputs:
ticket_id(number, required): ID of the ticketbody(string, required): Content of the note
- Inputs:
-
update_ticket_conversation: Update a conversation- Inputs:
conversation_id(number, required): ID of the conversationbody(string, required): Updated content
- Inputs:
-
view_ticket_summary: Get the summary of a ticket- Inputs:
ticket_id(number, required): ID of the ticket
- Inputs:
-
update_ticket_summary: Update the summary of a ticket- Inputs:
ticket_id(number, required): ID of the ticketbody(string, required): New summary content
- Inputs:
-
delete_ticket_summary: Delete the summary of a ticket- Inputs:
ticket_id(number, required): ID of the ticket
- Inputs:
-
get_agents: Get all agents- Inputs:
page(number, optional): Page numberper_page(number, optional): Number of agents per page
- Inputs:
-
view_agent: Get a single agent- Inputs:
agent_id(number, required): ID of the agent
- Inputs:
-
create_agent: Create a new agent- Inputs:
agent_fields(object, required): Agent details
- Inputs:
-
update_agent: Update an agent- Inputs:
agent_id(number, required): ID of the agentagent_fields(object, required): Fields to update
- Inputs:
-
search_agents: Search for agents- Inputs:
query(string, required): Search query
- Inputs:
-
list_contacts: Get all contacts- Inputs:
page(number, optional): Page numberper_page(number, optional): Contacts per page
- Inputs:
-
get_contact: Get a single contact- Inputs:
contact_id(number, required): ID of the contact
- Inputs:
-
search_contacts: Search for contacts- Inputs:
query(string, required): Search query
- Inputs:
-
update_contact: Update a contact- Inputs:
contact_id(number, required): ID of the contactcontact_fields(object, required): Fields to update
- Inputs:
-
list_companies: Get all companies- Inputs:
page(number, optional): Page numberper_page(number, optional): Companies per page
- Inputs:
-
view_company: Get a single company- Inputs:
company_id(number, required): ID of the company
- Inputs:
-
search_companies: Search for companies- Inputs:
query(string, required): Search query
- Inputs:
-
find_company_by_name: Find a company by name- Inputs:
name(string, required): Company name
- Inputs:
-
list_company_fields: Get all company fields- Inputs:
- None
- Inputs:
Getting Started
Installing via Smithery
To install freshdesk_mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @effytech/freshdesk_mcp --client claude
Prerequisites
- A Freshdesk account (sign up at freshdesk.com)
- Freshdesk API key
uvxinstalled (pip install uvorbrew install uv)
Configuration
- Generate your Freshdesk API key from the Freshdesk admin panel
- Set up your domain and authentication details
Usage with Claude Desktop
- Install Claude Desktop if you haven't already
- Add the following configuration to your
claude_desktop_config.json:
"mcpServers": {
"freshdesk-mcp": {
"command": "uvx",
"args": [
"freshdesk-mcp"
],
"env": {
"FRESHDESK_API_KEY": "<YOUR_FRESHDESK_API_KEY>",
"FRESHDESK_DOMAIN": "<YOUR_FRESHDESK_DOMAIN>"
}
}
}
Important Notes:
- Replace
YOUR_FRESHDESK_API_KEYwith your actual Freshdesk API key - Replace
YOUR_FRESHDESK_DOMAINwith your Freshdesk domain (e.g.,yourcompany.freshdesk.com)
Example Operations
Once configured, you can ask Claude to perform operations like:
- "Create a new ticket with subject 'Payment Issue for customer A101' and description as 'Reaching out for a payment issue in the last month for customer A101', where customer email is a101@acme.com and set priority to high"
- "Update the status of ticket #12345 to 'Resolved'"
- "List all high-priority tickets assigned to the agent John Doe"
- "List previous tickets of customer A101 in last 30 days"
Testing
For testing purposes, you can start the server manually:
uvx freshdesk-mcp --env FRESHDESK_API_KEY=<your_api_key> --env FRESHDESK_DOMAIN=<your_domain>
Troubleshooting
- Verify your Freshdesk API key and domain are correct
- Ensure proper network connectivity to Freshdesk 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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。