Skip to main content
Glama
lleontor705

forgespec-mcp

by lleontor705
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

tb_claim

Claim a task in ready status with all dependencies resolved for execution. Provide task ID and agent name.

Instructions

Claim a task for execution. Only claims tasks in 'ready' status with all dependencies resolved.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idYesTask ID to claim
agentYesAgent or developer claiming the task

Implementation Reference

  • src/tools/task-board.ts:194-251 (handler)
    The handler function for the 'tb_claim' tool. It claims a task by checking that the task exists, is in 'ready' or 'backlog' status, has all dependencies resolved (no blockers), and then updates the task status to 'in_progress' with an assignee and claimed_at timestamp.
    server.tool(
  "tb_claim",
  "Claim a task for execution. Only claims tasks in 'ready' status with all dependencies resolved.",
  {
    task_id: z.string().max(256).describe("Task ID to claim"),
    agent: z.string().max(256).regex(/^[a-zA-Z0-9_.-]+$/).describe("Agent or developer claiming the task"),
  },
  async ({ task_id, agent }) => {
    const db = getDb();
    const task = db.prepare(`SELECT * FROM tasks WHERE id = ?`).get(task_id) as Record<string, unknown> | undefined;

    if (!task) {
      return { content: [{ type: "text" as const, text: JSON.stringify({ error: "Task not found" }) }] };
    }

    if (task.status !== "ready" && task.status !== "backlog") {
      return {
        content: [{ type: "text" as const, text: JSON.stringify({ error: `Task is in "${task.status}" status, cannot claim` }) }],
      };
    }

    // Check dependencies
    const deps = JSON.parse(task.dependencies as string) as string[];
    if (deps.length > 0) {
      const placeholders = deps.map(() => "?").join(",");
      const blockers = db
        .prepare(`SELECT id, status FROM tasks WHERE id IN (${placeholders}) AND status != 'done'`)
        .all(...deps) as Record<string, unknown>[];

      if (blockers.length > 0) {
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify({
                error: "Blocked by unfinished dependencies",
                blockers: blockers.map((b) => ({ id: b.id, status: b.status })),
              }),
            },
          ],
        };
      }
    }

    const now = new Date().toISOString();
    db.prepare(
      `UPDATE tasks SET status = 'in_progress', assignee = ?, claimed_at = ?, updated_at = ? WHERE id = ?`
    ).run(agent, now, now, task_id);

    return {
      content: [
        {
          type: "text" as const,
          text: JSON.stringify({ claimed: true, task_id, agent, status: "in_progress" }),
        },
      ],
    };
  }
  • src/tools/task-board.ts:197-200 (schema)
    Input schema for the tb_claim tool, defining task_id (string max 256) and agent (string max 256, regex pattern for valid identifiers).
    {
  task_id: z.string().max(256).describe("Task ID to claim"),
  agent: z.string().max(256).regex(/^[a-zA-Z0-9_.-]+$/).describe("Agent or developer claiming the task"),
},
  • src/server.ts:18-20 (registration)
    Registration of the task board tools (including tb_claim) on the MCP server via registerTaskBoardTools.
    registerSddTools(server);
registerTaskBoardTools(server);
registerFileTools(server);
  • src/tools/task-board.ts:7-252 (registration)
    The registerTaskBoardTools function that registers all task board tools including tb_claim on the MCP server.
    export function registerTaskBoardTools(server: McpServer): void {
  // ── Create Board ───────────────────────────────────
  const TaskInputSchema = z.object({
    title: z.string().min(3).max(512),
    description: z.string().max(65536).default(""),
    priority: z.enum(TASK_PRIORITIES).default("p2"),
    spec_ref: z.string().max(512).optional(),
    acceptance_criteria: z.string().max(65536).default(""),
    dependencies: z.array(z.string()).default([]),
  });

  server.tool(
    "tb_create_board",
    "Create a new task board for a project. Optionally include tasks inline to create board + all tasks in a single atomic call (avoids N separate tb_add_task calls).",
    {
      project: z.string().max(256).regex(/^[a-zA-Z0-9_.-]+$/).describe("Project identifier (e.g. my-project)"),
      name: z.string().max(256).describe("Board name"),
      tasks: z.array(TaskInputSchema).max(100).optional().describe("Optional: tasks to create with the board. Each task: {title, description?, priority?, spec_ref?, acceptance_criteria?, dependencies?}. Dependencies reference other task titles or indices."),
    },
    async ({ project, name, tasks }) => {
      const db = getDb();
      const boardId = generateId("board");

      if (!tasks || tasks.length === 0) {
        db.prepare(
          `INSERT INTO boards (id, project, name) VALUES (?, ?, ?)`
        ).run(boardId, project, name);

        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify({ created: true, board_id: boardId, project, name, task_count: 0 }),
            },
          ],
        };
      }

      // Atomic: create board + all tasks in one transaction
      const insertBoard = db.prepare(
        `INSERT INTO boards (id, project, name) VALUES (?, ?, ?)`
      );
      const insertTask = db.prepare(
        `INSERT INTO tasks (id, board_id, title, description, priority, spec_ref, acceptance_criteria, dependencies, status)
         VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`
      );

      const taskIds: string[] = [];
      const taskIdMap: Record<string, string> = {};

      // Pre-generate IDs so dependencies can reference them
      for (let i = 0; i < tasks.length; i++) {
        const id = generateId("task");
        taskIds.push(id);
        taskIdMap[tasks[i].title] = id;
        taskIdMap[String(i)] = id;
      }

      const tx = db.transaction(() => {
        insertBoard.run(boardId, project, name);

        for (let i = 0; i < tasks.length; i++) {
          const t = tasks[i];
          // Resolve dependency references (by title or index) to generated IDs
          const resolvedDeps = t.dependencies.map((dep) => taskIdMap[dep] || dep);
          // Tasks with no dependencies start as "ready", others as "backlog"
          const status = resolvedDeps.length === 0 ? "ready" : "backlog";

          insertTask.run(
            taskIds[i],
            boardId,
            t.title,
            t.description,
            t.priority,
            t.spec_ref || null,
            t.acceptance_criteria,
            JSON.stringify(resolvedDeps),
            status
          );
        }
      });
      tx();

      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({
              created: true,
              board_id: boardId,
              project,
              name,
              task_count: tasks.length,
              task_ids: taskIds,
            }),
          },
        ],
      };
    }
  );

  // ── Add Task ───────────────────────────────────────
  server.tool(
    "tb_add_task",
    "Add a task to an existing board. Every task should reference a spec and have acceptance criteria.",
    {
      board_id: z.string().max(256).describe("Board ID"),
      title: z.string().min(3).max(512).describe("Task title"),
      description: z.string().max(65536).default("").describe("Task description"),
      priority: z.enum(TASK_PRIORITIES).default("p2").describe("Priority: p0 (critical), p1 (high), p2 (medium), p3 (low)"),
      spec_ref: z.string().max(512).optional().describe("Reference to spec document"),
      acceptance_criteria: z.string().max(65536).default("").describe("Acceptance criteria for completion"),
      dependencies: z.array(z.string()).default([]).describe("Task IDs this task depends on"),
    },
    async ({ board_id, title, description, priority, spec_ref, acceptance_criteria, dependencies }) => {
      const db = getDb();

      const board = db.prepare(`SELECT id FROM boards WHERE id = ?`).get(board_id);
      if (!board) {
        return {
          content: [{ type: "text" as const, text: JSON.stringify({ error: `Board ${board_id} not found` }) }],
        };
      }

      const id = generateId("task");
      db.prepare(
        `INSERT INTO tasks (id, board_id, title, description, priority, spec_ref, acceptance_criteria, dependencies)
         VALUES (?, ?, ?, ?, ?, ?, ?, ?)`
      ).run(id, board_id, title, description, priority, spec_ref || null, acceptance_criteria, JSON.stringify(dependencies));

      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({ created: true, task_id: id, board_id, title, priority }),
          },
        ],
      };
    }
  );

  // ── Get Board Status ───────────────────────────────
  server.tool(
    "tb_status",
    "Get the current status of a task board with all tasks grouped by status.",
    {
      board_id: z.string().describe("Board ID"),
    },
    async ({ board_id }) => {
      const db = getDb();
      const board = db.prepare(`SELECT * FROM boards WHERE id = ?`).get(board_id) as Record<string, unknown> | undefined;
      if (!board) {
        return {
          content: [{ type: "text" as const, text: JSON.stringify({ error: `Board ${board_id} not found` }) }],
        };
      }

      const tasks = db.prepare(
        `SELECT * FROM tasks WHERE board_id = ? ORDER BY
         CASE priority WHEN 'p0' THEN 0 WHEN 'p1' THEN 1 WHEN 'p2' THEN 2 WHEN 'p3' THEN 3 END,
         created_at ASC`
      ).all(board_id) as Record<string, unknown>[];

      const grouped: Record<string, unknown[]> = {};
      for (const status of TASK_STATUSES) {
        grouped[status] = tasks.filter((t) => t.status === status);
      }

      const summary = {
        total: tasks.length,
        by_status: Object.fromEntries(
          TASK_STATUSES.map((s) => [s, grouped[s].length])
        ),
      };

      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({ board, tasks: grouped, summary }),
          },
        ],
      };
    }
  );

  // ── Claim Task ─────────────────────────────────────
  server.tool(
    "tb_claim",
    "Claim a task for execution. Only claims tasks in 'ready' status with all dependencies resolved.",
    {
      task_id: z.string().max(256).describe("Task ID to claim"),
      agent: z.string().max(256).regex(/^[a-zA-Z0-9_.-]+$/).describe("Agent or developer claiming the task"),
    },
    async ({ task_id, agent }) => {
      const db = getDb();
      const task = db.prepare(`SELECT * FROM tasks WHERE id = ?`).get(task_id) as Record<string, unknown> | undefined;

      if (!task) {
        return { content: [{ type: "text" as const, text: JSON.stringify({ error: "Task not found" }) }] };
      }

      if (task.status !== "ready" && task.status !== "backlog") {
        return {
          content: [{ type: "text" as const, text: JSON.stringify({ error: `Task is in "${task.status}" status, cannot claim` }) }],
        };
      }

      // Check dependencies
      const deps = JSON.parse(task.dependencies as string) as string[];
      if (deps.length > 0) {
        const placeholders = deps.map(() => "?").join(",");
        const blockers = db
          .prepare(`SELECT id, status FROM tasks WHERE id IN (${placeholders}) AND status != 'done'`)
          .all(...deps) as Record<string, unknown>[];

        if (blockers.length > 0) {
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify({
                  error: "Blocked by unfinished dependencies",
                  blockers: blockers.map((b) => ({ id: b.id, status: b.status })),
                }),
              },
            ],
          };
        }
      }

      const now = new Date().toISOString();
      db.prepare(
        `UPDATE tasks SET status = 'in_progress', assignee = ?, claimed_at = ?, updated_at = ? WHERE id = ?`
      ).run(agent, now, now, task_id);

      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({ claimed: true, task_id, agent, status: "in_progress" }),
          },
        ],
      };
    }
  );
  • src/database/index.ts:12-30 (helper)
    The getDb helper function used by the tb_claim handler to obtain a SQLite database connection.
    export function getDb(): Database.Database {
  if (db) return db;

  fs.mkdirSync(path.dirname(DB_PATH), { recursive: true });

  db = new Database(DB_PATH);
  db.pragma("journal_mode = WAL");
  db.pragma("synchronous = normal");
  db.pragma("cache_size = -32000");
  db.pragma("temp_store = memory");
  db.pragma("busy_timeout = 5000");
  db.pragma("foreign_keys = ON");

  const versionInfo = db.prepare("SELECT sqlite_version() as version").get() as { version: string };
  console.error(`ForgeSpec MCP: SQLite ${versionInfo.version}, WAL mode enabled`);

  initSchema(db);
  return db;
}

Tool Definition Quality

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries burden. It mentions preconditions but does not disclose behavioral traits like state changes, reversibility, or ownership. Insufficient for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, no unnecessary wording, front-loaded with action and constraint.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks output schema and does not describe postconditions or error states. Preconditions are clear, but for a mutation tool, more completeness is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. Description adds no additional meaning beyond schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb 'claim', resource 'task', and includes constraints (only 'ready' status with resolved dependencies). Distinguishes from sibling tools like tb_add_task and tb_status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly specifies when to use (task in 'ready' status, dependencies resolved). Does not mention when not to use or alternatives, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lleontor705/forgespec-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server