board_get_tasks

Instructions

Implementation Reference

• src/tools/tasks.ts:5-91 (handler)

  The handler function registered as 'board_get_tasks'. Queries Firestore 'tasks' collection filtered by project_id and optional status/priority/assigned_agent/include_done, sorts by priority (critical first), and returns JSON stringified task objects.

  export function registerTaskTools(server: McpServer, db: Firestore) {
    server.tool(
      "board_get_tasks",
      "List tasks in a project with optional filters. Results are sorted client-side by priority (critical → low) — not by creation time. By default excludes done tasks (pass include_done=true or set status='done' to see them). Use this for mid-session checks: almost always pass a status filter (e.g., 'in_progress' or 'todo') to keep responses tight. For a single task by ID, use board_get_task instead. Returns an array of task objects with id, project_id, title, description, status, priority, assigned_agent, parent_task_id, depends_on, riper_mode, metadata, and ISO timestamps (created_at, updated_at, started_at, completed_at).",
      {
        project_id: z.string().describe("Project ID (from board_get_projects) whose tasks to list"),
        status: z
          .enum(["backlog", "todo", "in_progress", "blocked", "review", "done"])
          .optional()
          .describe("Filter to a single status. Omit to return all non-done tasks (unless include_done=true)."),
        priority: z
          .enum(["critical", "high", "medium", "low"])
          .optional()
          .describe("Filter to a single priority. Omit to return all priorities."),
        assigned_agent: z
          .string()
          .optional()
          .describe("Filter to tasks assigned to this agent name (exact match). Omit to return all assignments."),
        include_done: z
          .boolean()
          .optional()
          .describe("Include tasks with status='done' (default false — done tasks are hidden to keep responses small). Ignored if an explicit status filter is set."),
      },
      async ({ project_id, status, priority, assigned_agent, include_done }) => {
        let query: FirebaseFirestore.Query<FirebaseFirestore.DocumentData> = db
          .collection("tasks")
          .where("project_id", "==", project_id);
  
        if (status) {
          query = query.where("status", "==", status);
        } else if (!include_done) {
          query = query.where("status", "!=", "done");
        }
  
        if (priority) {
          query = query.where("priority", "==", priority);
        }
  
        if (assigned_agent) {
          query = query.where("assigned_agent", "==", assigned_agent);
        }
  
        const snapshot = await query.get();
        const priorityOrder: Record<string, number> = {
          critical: 0,
          high: 1,
          medium: 2,
          low: 3,
        };
  
        const tasks = snapshot.docs
          .map((doc) => {
            const data = doc.data();
            return {
              id: doc.id,
              project_id: data.project_id as string,
              title: data.title as string,
              description: data.description as string | null,
              status: data.status as string,
              priority: data.priority as string,
              assigned_agent: data.assigned_agent as string | null,
              parent_task_id: data.parent_task_id as string | null,
              depends_on: data.depends_on as string[],
              riper_mode: data.riper_mode as string | null,
              metadata: data.metadata as Record<string, unknown>,
              created_at: data.created_at?.toDate?.()?.toISOString() ?? null,
              updated_at: data.updated_at?.toDate?.()?.toISOString() ?? null,
              started_at: data.started_at?.toDate?.()?.toISOString() ?? null,
              completed_at: data.completed_at?.toDate?.()?.toISOString() ?? null,
            };
          })
          .sort(
            (a, b) =>
              (priorityOrder[a.priority] ?? 99) -
              (priorityOrder[b.priority] ?? 99)
          );
  
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(tasks, null, 2),
            },
          ],
        };
      }
    );

• src/tools/tasks.ts:9-27 (schema)

  Zod schema defining input parameters: required project_id, optional status (enum), priority (enum), assigned_agent (string), and include_done (boolean) for filtering tasks.

  {
    project_id: z.string().describe("Project ID (from board_get_projects) whose tasks to list"),
    status: z
      .enum(["backlog", "todo", "in_progress", "blocked", "review", "done"])
      .optional()
      .describe("Filter to a single status. Omit to return all non-done tasks (unless include_done=true)."),
    priority: z
      .enum(["critical", "high", "medium", "low"])
      .optional()
      .describe("Filter to a single priority. Omit to return all priorities."),
    assigned_agent: z
      .string()
      .optional()
      .describe("Filter to tasks assigned to this agent name (exact match). Omit to return all assignments."),
    include_done: z
      .boolean()
      .optional()
      .describe("Include tasks with status='done' (default false — done tasks are hidden to keep responses small). Ignored if an explicit status filter is set."),
  },

• src/index.ts:29-29 (registration)

  Registration call that wires registerTaskTools into the MCP server at startup.

  registerTaskTools(server, db);