Skip to main content
Glama
zeeweebee

Minecraft MCP Server

by zeeweebee

place-block

Place blocks at specific coordinates in Minecraft using X, Y, Z positions and face directions to build structures or modify terrain.

Instructions

Place a block at the specified position

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
xYesX coordinate
yYesY coordinate
zYesZ coordinate
faceDirectionNoDirection to place against (default: 'down')

Implementation Reference

  • The async handler function that implements the place-block tool logic: checks if position is free, defines possible faces for placement, prioritizes requested faceDirection, iterates over faces to find reference block, moves closer if can't see, looks at position, and attempts bot.placeBlock.
    async ({ x, y, z, faceDirection = 'down' }: { x: number, y: number, z: number, faceDirection?: FaceDirection }): Promise<McpResponse> => {
      try {
        const placePos = new Vec3(x, y, z);
        const blockAtPos = bot.blockAt(placePos);
        if (blockAtPos && blockAtPos.name !== 'air') {
          return createResponse(`There's already a block (${blockAtPos.name}) at (${x}, ${y}, ${z})`);
        }
    
        const possibleFaces: FaceOption[] = [
          { direction: 'down', vector: new Vec3(0, -1, 0) },
          { direction: 'north', vector: new Vec3(0, 0, -1) },
          { direction: 'south', vector: new Vec3(0, 0, 1) },
          { direction: 'east', vector: new Vec3(1, 0, 0) },
          { direction: 'west', vector: new Vec3(-1, 0, 0) },
          { direction: 'up', vector: new Vec3(0, 1, 0) }
        ];
    
        // Prioritize the requested face direction
        if (faceDirection !== 'down') {
          const specificFace = possibleFaces.find(face => face.direction === faceDirection);
          if (specificFace) {
            possibleFaces.unshift(possibleFaces.splice(possibleFaces.indexOf(specificFace), 1)[0]);
          }
        }
    
        // Try each potential face for placing
        for (const face of possibleFaces) {
          const referencePos = placePos.plus(face.vector);
          const referenceBlock = bot.blockAt(referencePos);
    
          if (referenceBlock && referenceBlock.name !== 'air') {
            if (!bot.canSeeBlock(referenceBlock)) {
              // Try to move closer to see the block
              const goal = new goals.GoalNear(referencePos.x, referencePos.y, referencePos.z, 2);
              await bot.pathfinder.goto(goal);
            }
    
            await bot.lookAt(placePos, true);
    
            try {
              await bot.placeBlock(referenceBlock, face.vector.scaled(-1));
              return createResponse(`Placed block at (${x}, ${y}, ${z}) using ${face.direction} face`);
            } catch (placeError) {
              console.error(`Failed to place using ${face.direction} face: ${(placeError as Error).message}`);
              continue;
            }
          }
        }
    
        return createResponse(`Failed to place block at (${x}, ${y}, ${z}): No suitable reference block found`);
      } catch (error) {
        return createErrorResponse(error as Error);
      }
    }
  • Zod input schema for the place-block tool defining required numeric coordinates x, y, z and optional faceDirection enum.
    {
      x: z.number().describe("X coordinate"),
      y: z.number().describe("Y coordinate"),
      z: z.number().describe("Z coordinate"),
      faceDirection: z.enum(['up', 'down', 'north', 'south', 'east', 'west']).optional().describe("Direction to place against (default: 'down')")
    },
  • src/bot.ts:341-404 (registration)
    Registration of the place-block tool via server.tool() call within registerBlockTools function, including name, description, schema, and inline handler.
    server.tool(
      "place-block",
      "Place a block at the specified position",
      {
        x: z.number().describe("X coordinate"),
        y: z.number().describe("Y coordinate"),
        z: z.number().describe("Z coordinate"),
        faceDirection: z.enum(['up', 'down', 'north', 'south', 'east', 'west']).optional().describe("Direction to place against (default: 'down')")
      },
      async ({ x, y, z, faceDirection = 'down' }: { x: number, y: number, z: number, faceDirection?: FaceDirection }): Promise<McpResponse> => {
        try {
          const placePos = new Vec3(x, y, z);
          const blockAtPos = bot.blockAt(placePos);
          if (blockAtPos && blockAtPos.name !== 'air') {
            return createResponse(`There's already a block (${blockAtPos.name}) at (${x}, ${y}, ${z})`);
          }
    
          const possibleFaces: FaceOption[] = [
            { direction: 'down', vector: new Vec3(0, -1, 0) },
            { direction: 'north', vector: new Vec3(0, 0, -1) },
            { direction: 'south', vector: new Vec3(0, 0, 1) },
            { direction: 'east', vector: new Vec3(1, 0, 0) },
            { direction: 'west', vector: new Vec3(-1, 0, 0) },
            { direction: 'up', vector: new Vec3(0, 1, 0) }
          ];
    
          // Prioritize the requested face direction
          if (faceDirection !== 'down') {
            const specificFace = possibleFaces.find(face => face.direction === faceDirection);
            if (specificFace) {
              possibleFaces.unshift(possibleFaces.splice(possibleFaces.indexOf(specificFace), 1)[0]);
            }
          }
    
          // Try each potential face for placing
          for (const face of possibleFaces) {
            const referencePos = placePos.plus(face.vector);
            const referenceBlock = bot.blockAt(referencePos);
    
            if (referenceBlock && referenceBlock.name !== 'air') {
              if (!bot.canSeeBlock(referenceBlock)) {
                // Try to move closer to see the block
                const goal = new goals.GoalNear(referencePos.x, referencePos.y, referencePos.z, 2);
                await bot.pathfinder.goto(goal);
              }
    
              await bot.lookAt(placePos, true);
    
              try {
                await bot.placeBlock(referenceBlock, face.vector.scaled(-1));
                return createResponse(`Placed block at (${x}, ${y}, ${z}) using ${face.direction} face`);
              } catch (placeError) {
                console.error(`Failed to place using ${face.direction} face: ${(placeError as Error).message}`);
                continue;
              }
            }
          }
    
          return createResponse(`Failed to place block at (${x}, ${y}, ${z}): No suitable reference block found`);
        } catch (error) {
          return createErrorResponse(error as Error);
        }
      }
    );

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior2/5

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

The description is minimal and does not disclose important behavioral traits such as whether the block is consumed from inventory, whether permissions are required, or whether there are any side effects. No annotations are present to compensate.

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

Conciseness4/5

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

The description is extremely concise, using a single sentence. While it is not verbose, it efficiently communicates the core action without extraneous information.

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?

For a simple tool, the description is minimally adequate. However, it omits information about what block is placed (e.g., the held item) and any success indicators, leaving the agent with incomplete context.

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 description coverage is 100%, so the schema already documents all parameters. The description adds no additional meaning or context beyond what the schema provides, achieving baseline adequacy.

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?

The description clearly states the action ('Place') and the resource ('a block'), and is distinctive from sibling tools like 'dig-block' or 'craft-item'. It leaves no ambiguity about the tool's function.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. For example, it does not mention that the block must be in the player's inventory, or that this tool is for building while 'dig-block' is for removal.

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