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_ticketsBrowse and search tickets with advanced filtering capabilities
get_ticket_detailsRetrieve comprehensive ticket information including history and attachments
create_ticketCreate new tickets with proper categorization and metadata
update_ticketModify ticket properties, status, or assignments
add_commentAdd comments, updates, or internal notes to tickets
analyze_trendsIdentify patterns and trends in ticket data for insights

list_tickets​

Browse and search tickets with advanced filtering capabilities

Parameters:

  • integration: Target ticketing platform integration (required)
  • status: Filter by ticket status (open, in_progress, resolved, closed)
  • priority: Filter by priority level (critical, high, medium, low)
  • assignee: Filter by assigned user or team
  • created_after: Filter tickets created after specific date
  • labels: Filter by labels or tags
  • type: Filter by ticket type (incident, problem, change, service_request)
  • page: Pagination control
  • limit: Number of results per page

get_ticket_details​

Retrieve comprehensive ticket information including history and attachments

Parameters:

  • integration: Target ticketing platform integration (required)
  • ticket_id: Unique ticket identifier (required)
  • include_comments: Include all comments and updates
  • include_attachments: Include attachment metadata
  • include_history: Include complete change history
  • include_related: Include linked or related tickets

create_ticket​

Create new tickets with proper categorization and metadata

Parameters:

  • integration: Target ticketing platform integration (required)
  • title: Ticket title/summary (required)
  • description: Detailed ticket description (required)
  • type: Ticket type (incident, problem, change, service_request)
  • priority: Priority level (critical, high, medium, low)
  • assignee: Initial assignee (user or team)
  • labels: Tags for categorization
  • custom_fields: Platform-specific custom fields
  • parent_ticket: Link to parent ticket for sub-tasks

update_ticket​

Modify ticket properties, status, or assignments

Parameters:

  • integration: Target ticketing platform integration (required)
  • ticket_id: Ticket to update (required)
  • status: New ticket status
  • assignee: Reassign to different user/team
  • priority: Update priority level
  • labels: Add or remove labels
  • custom_fields: Update custom field values
  • resolution: Set resolution details

add_comment​

Add comments, updates, or internal notes to tickets

Parameters:

  • integration: Target ticketing platform integration (required)
  • ticket_id: Target ticket (required)
  • comment: Comment text (required)
  • visibility: Public or internal comment
  • attachments: Files to attach
  • mentions: Users to notify
  • work_log: Time tracking information

Identify patterns and trends in ticket data for insights

Parameters:

  • integration: Target ticketing platform integration (required)
  • time_range: Period to analyze
  • group_by: Dimensions for analysis (category, team, priority)
  • metrics: Metrics to calculate (volume, resolution_time, reopen_rate)
  • filters: Additional filters for analysis
  • include_predictions: Enable predictive analytics

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",
        "http://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