screen_record_start

SERVERLocal SOURCElocal-mcp

High RISK CLASS

Category Execute

Parameters 41 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-local-mcp-local-mcp/screen-record-start.md

WHAT IT DOES

What screen_record_start does on Local

AI agents invoke screen_record_start to trigger actions in Local. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`fps`	integer	—	Frames per second (default 60).
`target`	object	Yes	What to capture.
`output_path`	string	—	Where to write the .mov (default: temp file, returned by stop).
`show_cursor`	boolean	—	Default true.

Parameters from the server's own tool schema.

RISK

Why screen_record_start is rated High

screen_record_start executes a system-level screen recording operation that captures sensitive visual data from the user's display. This is Execute rather than Read because it actively triggers and maintains an ongoing recording session with side effects (resource consumption, permission requirements, persistent session state).

From the tool's definition Tool description states it 'Begins a screen recording (ScreenCaptureKit) of a display, window, or region' and 'Returns a session_id used by record_marker and screen_record_stop.' This is a direct trigger of an external operation (screen recording) whose…

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs screen_record_start safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For screen_record_start, this is the rule to start with:

screen_record_start Rate-limited

screen_record_start stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "screen_record_start": {
      "limits": [
        {
          "counter": "screen_record_start_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every screen_record_start call is checked against it from then on.

FAQ

Questions about screen_record_start

What does the screen_record_start tool do? +

Begins a screen recording (ScreenCaptureKit) of a display, window, or region. Single active session in v1 — a second start returns already_recording. Returns a session_id used by record_marker and screen_record_stop. Requires Screen Recording permission; without it returns an explicit permission_required error, never a silent no-op. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does screen_record_start accept? +

screen_record_start accepts 4 parameters: fps, target, output_path, show_cursor. Required: target. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on screen_record_start? +

Register the Local MCP server in PolicyLayer and add a rule for screen_record_start: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Local. Nothing to install.

What risk level is screen_record_start? +

screen_record_start is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit screen_record_start? +

Yes. Add a rate_limit block to the screen_record_start rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block screen_record_start completely? +

Set action: deny in the PolicyLayer policy for screen_record_start. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides screen_record_start? +

screen_record_start is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Local, and thousands of servers like it.

This server

All 234 Local tools → High-risk tools on this server →

Across the catalogue

start_devtools_monitoring on Percepta MCP Server →team_manager_start_room on Team Manager MCP →start_etw_trace on Procmon → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →