tpm-mcp

Instructions

Implementation Reference

• src/tpm_mcp/server.py:75-141 (registration)

  Registration of the 'ticket_create' tool in list_tools(), defining its name, description, and JSON inputSchema matching TicketCreate fields.
  Tool( name="ticket_create", description="""PROJECT MANAGEMENT (TPM): Create a new ticket, epic, or issue to track. USE THIS TOOL WHEN: - User says ":TPM: Add X feature to the roadmap" - User wants to add a new feature/ticket/issue - User says "add ticket for X" or "create feature for Y" - Breaking down work into trackable items - User asks to scope out or define new work - User discusses new work that should be tracked Use roadmap_view first to get the project_id. Tickets are high-level work items (like Jira epics/stories). ID AUTO-GENERATION: IDs are always auto-generated as {PREFIX}-{NNN} (e.g., FEAT-001, ISSUE-042). The number is automatically incremented based on existing tickets with that prefix. OPTIONAL PREFIX PARAMETER: Provide a prefix to categorize the ticket type: - FEAT: New features or capabilities - ISSUE: Bugs, problems, or issues to fix - TASK: General tasks or chores - INFRA: Infrastructure or DevOps work - DOC: Documentation tasks If no prefix is provided, uses the project ID as the prefix (e.g., FRONTEND-001, BACKEND-042).""", inputSchema={ "type": "object", "properties": { "project_id": { "type": "string", "description": "Project ID (use project_list to find) case-insensitive", }, "prefix": { "type": "string", "description": "Optional prefix for ticket ID (e.g., FEAT, ISSUE, INFRA). Number is auto-generated. If omitted, uses project ID as prefix.", }, "title": {"type": "string", "description": "Ticket title"}, "description": { "type": "string", "description": "Detailed description of the ticket", }, "status": { "type": "string", "enum": ["backlog", "planned", "in-progress", "done", "blocked"], "description": "Ticket status (default: backlog)", }, "priority": { "type": "string", "enum": ["critical", "high", "medium", "low"], "description": "Priority level (default: medium)", }, "tags": { "type": "array", "items": {"type": "string"}, "description": "Tags for categorization", }, "assignees": { "type": "array", "items": {"type": "string"}, "description": "Who is working on this", }, }, "required": ["project_id", "title"], }, ),
• src/tpm_mcp/server.py:525-540 (handler)

  Handler code in _handle_tool: parses arguments into TicketCreate model and calls db.create_ticket, returns confirmation.
  if name == "ticket_create": ticket = db.create_ticket( TicketCreate( project_id=args["project_id"], title=args["title"], prefix=args.get("prefix"), description=args.get("description"), status=TicketStatus(args.get("status", "backlog")), priority=Priority(args.get("priority", "medium")), tags=args.get("tags"), assignees=args.get("assignees"), ) ) # Return minimal confirmation to avoid context bleed return f"Created ticket: {ticket.id} - {ticket.title} [{ticket.status.value}]"
• src/tpm_mcp/models.py:87-99 (schema)

  Pydantic schema definition for TicketCreate, used for input validation in tool handler.
  class TicketCreate(BaseModel): project_id: str title: str prefix: str | None = None # Optional prefix for auto-generated ID (e.g., FEAT, ISSUE, INFRA) description: str | None = None status: TicketStatus = TicketStatus.BACKLOG priority: Priority = Priority.MEDIUM assignees: list[str] | None = None tags: list[str] | None = None related_repos: list[str] | None = None acceptance_criteria: list[str] | None = None blockers: list[str] | None = None metadata: dict[str, Any] | None = None
• src/tpm_mcp/db.py:277-336 (helper)

  Database helper method TrackerDB.create_ticket: generates sequential ID with prefix, inserts ticket record into SQLite, returns Ticket model.
  def create_ticket(self, data: TicketCreate) -> Ticket: normalized_project_id = self._normalize_id(data.project_id) # Check if a case-insensitive match already exists for project_id existing_project = self.conn.execute( "SELECT id FROM projects WHERE LOWER(id) = ?", (normalized_project_id,) ).fetchone() if existing_project: project_id = existing_project["id"] # Use existing project ID else: project_id = normalized_project_id # Use normalized project_id for new entries # Determine prefix for ID generation if data.prefix: # Use provided prefix (e.g., FEAT, ISSUE, INFRA) prefix = data.prefix.upper().replace(" ", "").replace("-", "").replace("_", "") else: # Auto-generate prefix from project ID project = self.get_project(project_id) if project: prefix = project.id.upper().replace(" ", "").replace("-", "").replace("_", "") else: prefix = "TICKET" next_num = self._get_next_ticket_number(prefix) id = f"{prefix}-{next_num:03d}" now = self._now() self.conn.execute( """INSERT INTO tickets (id, project_id, title, description, status, priority, created_at, assignees, tags, related_repos, acceptance_criteria, blockers, metadata) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""", ( id, project_id, data.title, data.description, data.status.value, data.priority.value, now, _to_json(data.assignees), _to_json(data.tags), _to_json(data.related_repos), _to_json(data.acceptance_criteria), _to_json(data.blockers), _to_json(data.metadata), ), ) self.conn.commit() return Ticket( id=id, project_id=project_id, title=data.title, description=data.description, status=data.status, priority=data.priority, created_at=datetime.fromisoformat(now), assignees=data.assignees, tags=data.tags, related_repos=data.related_repos, acceptance_criteria=data.acceptance_criteria, blockers=data.blockers, metadata=data.metadata, )