Skip to main content

Model Context Protocol (MCP)

Unizo offers an MCP server that integrates ticketing platforms with any LLM provider supporting the MCP protocol. This enables your AI agent to manage tickets, analyze support patterns, and automate customer service workflows across Jira, ServiceNow, Zendesk, and other ticketing systems via a single MCP server.

Supported Tools & Use Cases​

The following tools are available in the Ticketing MCP Server:

Tool NameDescription
list_servicesGet list of available ticket services
list_integrationsGet integrations for a specific service
list_organizationGet organizations for an integration
list_collectionsGet collections (projects/sprints/epics) for an organization
list_ticketsBrowse and search tickets within collections
create_ticketsCreate new tickets with proper categorization
confirm_ticket_creationExtract and confirm ticket details from natural language

Tool Reference​

list_services​

Get list of available ticket services

Parameters:
None

Returns:
List of available services (e.g., Jira, ServiceNow, Zendesk, GitHub Issues)

list_integrations​

Get integrations for a specific service

Parameters:

  • service : Name of the service (e.g., "jira", "servicenow") (required)

Returns:
List of integrations available for the specified service

list_organizations​

Get organizations for an integration

Parameters:

  • integration_id : Unique identifier of the integration (required)

Returns:
List of organizations accessible through the integration

list_collections​

Get collections (projects, sprints, epics, etc.) for an organization

Parameters:

  • integration_id : Integration identifier (required)
  • organization_id : Organization identifier (required)

Returns:
List of collections within the organization

list_tickets​

Browse and search tickets within a collection

Parameters:

  • integration_id : Integration identifier (required)
  • organization_id : Organization identifier (auto-selected if only one available)
  • collection_id : Collection identifier (auto-selected if only one available)

Returns:
List of tickets with pagination information

create_ticket​

Create a new ticket in the specified collection

Parameters:

  • integration_id : Integration identifier (required)
  • organization_id : Organization identifier (required)
  • collection_id : Collection identifier (required)
  • ticket_name : Title/summary of the ticket (required)
  • ticket_description : Detailed description
  • ticket_status : Initial status (open, closed, in_progress, resolved)
  • ticket_priority : Priority level (low, medium, high, critical)
  • ticket_type : Type of ticket (bug, feature, task, security, enhancement)

confirm_ticket_creation​

Extract and confirm ticket details from natural language input

Parameters:

  • user_request : Natural language description of the ticket (required)

Returns:
Extracted ticket details and available services

Installation​

Prerequisites​

  • A Unizo API key
  • An active Ticketing integration (GitHub, GitHub Enterprise, GitLab, GitLab (Self-Managed), Bitbucket, Azure DevOps, Salesforce, Jira, Jira Data Center, Trello)
  • Node.js v20 or higher

MCP Configuration​

Here is an example configuration for setting up the Unizo SCM MCP server:

{
  "mcpServers": {
    "unizo-ticketing": {
        "command": "npx",
      "args": [
        "mcp-remote",
        "https://api.unizo.ai/mcp/ticketing",
        "--allow-http",
        "--header",
        "apikey:${UNIZO_API_KEY}"
      ],
      "env": {
        "UNIZO_API_KEY": "your_api_key"
      }
    }
  }
}

Client Setup​

For detailed setup instructions with specific AI clients:

Environment Variables​

The following environment variables are required:

Error Handling​

All tools return errors in a consistent format:

{
  "error": {
    "code": "REPOSITORY_NOT_FOUND",
    "message": "Repository 'example/repo' not found"
  }
}

Common error codes:

  • INTEGRATION_NOT_FOUND: Invalid integration ID
  • REPOSITORY_NOT_FOUND: Repository doesn't exist or no access
  • BRANCH_NOT_FOUND: Branch doesn't exist
  • FILE_NOT_FOUND: File path not found
  • RATE_LIMIT_EXCEEDED: API rate limit reached
  • UNAUTHORIZED: Invalid credentials or permissions