windows2-mcp

Overview Schema Source Related Servers Discussions Admin

start_recording_screen

Start recording your Windows screen using FFmpeg. Automatically restarts any existing recording; use stop to end and retrieve the video file.

Instructions

Start an FFmpeg-based screen recording. If a recording is already running it is stopped and restarted by default. Call stop_recording_screen to end it and retrieve the video.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_recording_screen"
  }
}

Input Schema

Name	Required	Description
`preset`	No	FFmpeg encoding preset (e.g. "ultrafast", "medium")
`videoFps`	No	Frames per second
`timeLimit`	No	Maximum recording duration in seconds
`audioInput`	No	Audio input device name to record from
`outputPath`	No	Path to a .mp4 file to write to. Defaults to a temp file.
`videoFilter`	No	Raw FFmpeg -vf filter string
`forceRestart`	No	If a recording is already running, stop and restart it
`captureClicks`	No	Highlight mouse clicks in the recording
`captureCursor`	No	Include the mouse cursor in the recording

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Aug 18, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only provide destructiveHint=false, so description carries the behavioral burden. The description discloses the restart behavior and the need to call stop_recording_screen. However, it does not mention whether the recording can be paused, what happens on errors (e.g., missing path permissions), or the format of returned data. A 4 is appropriate as it adds significant context beyond annotations but has minor gaps.

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 two sentences, which is concise and front-loaded with the core purpose. Every sentence adds value, though the second sentence could be slightly more direct about the stop call. No waste, but slightly more context on restart could be merged.

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

Completeness4/5

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

With 9 parameters, no output schema, and a 'stop' sibling, the description explains the lifecycle (start/stop/restart) but lacks detail on edge cases (e.g., concurrent recordings, permission errors). It is sufficient for typical use but not exhaustive. A 4 reflects good coverage given the complexity.

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 baseline is 3. The description does not add extra meaning to the parameters beyond what their schema descriptions already provide. It lists nothing about parameter usage, so no extra credit is earned.

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 identifies the tool as starting an FFmpeg-based screen recording, distinguishes it from stop_recording_screen, and mentions the default restart behavior. The verb 'start' and resource 'recording' are explicit and unambiguous.

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?

The description explicitly says when to use this tool (start recording) and when to use the sibling stop_recording_screen (end and retrieve video). It also clearly states the default restart behavior if a recording is already running, guiding the agent on usage flow.

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

Deploy Server