screen-recorder-mcp

Overview Schema Source Related Servers Discussions Admin

start_recording

Record a chosen app window, a cropped area, or an entire monitor to MP4 with optional system or microphone audio, cursor capture, and a countdown delay.

Instructions

Start recording a window or monitor to MP4 (H.264).

    target: window title / process name / window_id, or `monitor:N` (see list_targets).
    region: optional {x, y, width, height} relative to the target, usually from pick_region.
    audio: "none" (default), "system" or "mic" — only when the user asked for audio.
    capture: "auto" (default: GPU capture, CPU if the GPU can't start), "gpu", or "cpu"
             (Windows only; no GPU use at all, no cursor in the video).
    delay_seconds: countdown before capture starts (0 default; the user sees it on screen).
    The user sees the recording toolbar of the desktop app, if it is running.

Input Schema

Name	Required	Default
`fps`	No
`audio`	No	none
`region`	No
`target`	Yes
`capture`	No	auto
`output_dir`	No
`delay_seconds`	No
`capture_cursor`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it explains GPU-first with CPU fallback, that cpu capture is Windows-only and produces no cursor in the video, and that delay_seconds is a user-visible countdown and the desktop toolbar may appear. It omits failure/error behavior and where files land by default, keeping it out of the top band.

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 one-line purpose is front-loaded and the per-parameter bullets are terse and scannable, with no filler prose. The trailing note about the desktop toolbar is loosely related but slightly detached from the calling task.

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?

An output schema exists, so return values need no explanation, but for an eight-parameter capture tool with zero annotation coverage the description leaves fps, output_dir and capture_cursor unexplained and never says how to reference or retrieve the finished recording (list_recordings/stop_recording). Adequate to initiate a basic call, insufficient for full control.

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 0%, so the description must compensate — and it does for five of eight params, adding syntax the schema lacks (`monitor:N`, region relative to target, audio enum values, capture mode semantics, visible countdown). However fps, output_dir and capture_cursor are never mentioned, leaving a substantial gap on a multi-param tool.

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?

Opens with a specific verb, resource and output format: "Start recording a window or monitor to MP4 (H.264)." It immediately distinguishes scope (window vs monitor) and defers target enumeration to the named sibling list_targets, so an agent can separate it from pause_recording/stop_recording without opening a schema.

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?

Gives concrete when-to-use routing: targets come from list_targets, regions "usually from pick_region," and audio should be set only when the user asked for it. It stops short of explicit exclusions (e.g., don't call this if a recording is already active — use recording_status), so it is a clear-context 4 rather than a full 5.

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

Deploy Server