Skip to main content
Glama
screen-record-mcp

screen-record-mcp

by strubedo

Start Recording

start_recording

Record screen video with or without system audio to an MP4 file and choose a custom output path; first use may require one-time KDE screen-share approval.

Instructions

Start a screen recording (with system audio by default, or video-only) to a given output .mp4 path. The first call on a fresh system may require the user to approve a one-time KDE screen-share permission dialog on their desktop - this cannot be approved programmatically.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
audioNoRecord system audio alongside video. Set false for video-only.
outputNoOutput .mp4 path. Defaults to a timestamped filename in the current directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral load, and it does disclose two valuable facts: system audio is captured by default, and a first-run KDE screen-share dialog requires interactive user approval that cannot be automated. It stops short of stating whether the call blocks until recording ends, what happens on a duplicate start, or what the response contains.

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?

Two sentences, front-loaded with the action and artifact, then the operational caveat. Every clause carries information, with only slight redundancy in re-stating the audio default already given by the schema.

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 two-optional-parameter tool with no output schema, the essentials are present, but an agent still lacks the lifecycle picture: whether the call returns immediately, whether it fails if a recording is active, and how to confirm success beyond calling the sibling status tool.

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 both the 'audio' default and the timestamped-filename behavior of 'output' are already documented in the input schema. The description's restatement of 'system audio by default, or video-only' adds no meaning beyond that; baseline 3 applies.

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

Purpose4/5

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

The description names a specific verb and resource — 'Start a screen recording' — and adds the output artifact ('a given output .mp4 path') plus the audio/video-only distinction. Its purpose is unmistakable against the sibling names stop_recording and check_recording_status, though it never explicitly states the division of labor with them.

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

Usage Guidelines3/5

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

Usage is implied by the verb and by the permission-dialog caveat, but there is no explicit guidance on when to prefer this tool, what to do if a recording is already in progress, or that check_recording_status exists for polling. An agent can infer the call site but must guess at preconditions.

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