Skip to main content
Glama

mc_record_video

Capture a short video burst of the Minecraft client framebuffer to debug temporal rendering issues like animation glitches or shader bugs. Output as a grid or individual frames.

Instructions

Capture a short burst of the Minecraft client framebuffer for debugging temporal rendering issues — animation glitches, shader bugs, particles, sub-tick artifacts that mc_screenshot can't resolve. Use the Read tool to view the result.

Two output modes:

  • "grid" (default): one composed JPEG laid out as a frame grid. Best for Claude — the whole recording in a single Read.

  • "frames": N separate JPEGs. Use only when you need to inspect individual frames closely.

Caps (validated mod-side, request rejected if exceeded):

  • frames: 1..300 (≈5 s at 60 Hz)

  • interval: "frame" (every render tick) or milliseconds >= 1

  • downscale: integer >= 1 (default 2)

  • quality: [0.05, 1.0] (default 0.75)

Pick interval deliberately. Default to a numeric ms (50–100 ms is usually right) — smooth motion, never drops frames. Use "frame" only when sub-tick detail matters; at that cadence the encoder may fall behind and the response's "dropped" count tells you how many frames were skipped.

The mod and the MCP server must run on the same machine for the returned paths to be readable here. Files land under /debugbridge-recordings//.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
framesYesNumber of frames to capture, 1..300. Required.
outputNo"grid" (one composed JPEG, default) or "frames" (N separate JPEGs).
qualityNoJPEG quality in [0.05, 1.0]. Default 0.75. In "grid" mode applies once to the composed image.
gridColsNoColumns in grid layout. Default ceil(sqrt(frames)). Only used in "grid" mode.
intervalNo"frame" for every render tick (~60 Hz), or milliseconds (number, >= 1). Default "frame". Recommended: 50–100 ms unless you specifically need sub-tick detail.
downscaleNoInteger downscale factor. Default 2 (half each axis).
Behavior5/5

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

With no annotations, the description fully discloses behavior: output modes, caps (frames, interval, downscale, quality), that request is rejected if caps exceeded, that 'frame' may drop frames and the 'dropped' response field, and file storage location.

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 well-structured with clear sections and front-loads the purpose. It is slightly lengthy but every sentence is informative; minor redundancy in caps listing could be tightened.

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

Completeness5/5

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

Given the tool's complexity (6 parameters, no output schema, no annotations), the description covers all necessary aspects: purpose, parameter behavior, output modes, usage guidance, technical constraints, and differential from siblings.

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

Parameters5/5

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

Schema coverage is 100%, but the description adds significant value beyond the schema: recommended interval values, default for downscale (2), default quality (0.75), default gridCols calculation, and that quality applies once in grid mode.

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 tool captures a short burst of the Minecraft framebuffer for debugging temporal rendering issues, explicitly distinguishing it from mc_screenshot for static captures.

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

Usage Guidelines5/5

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

It explains when to use (temporal issues), when not to (use mc_screenshot instead), and provides concrete recommendations like defaulting to 50-100 ms interval rather than 'frame', and notes the requirement for mod/server on the same machine.

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/use-ai-for-mc/mcdev-mcp'

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