record_marker
Drops a named marker into the active recording's timeline. t_ms is elapsed ms since recording start. Provide bounds (global points, top-left) to zoom toward an element, or omit for full-frame. note becomes a caption source. Returns no_active_session if nothing is recording.
This record as markdown: /tools/com-local-mcp-local-mcp/record-marker.md
What record_marker does on Local
AI agents use record_marker to create or update resources in Local, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Local environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Marker name, e.g. open_tray, act2_calendar_create. |
note | string | — | Free text → caption source. |
bounds | object | — | Optional {x,y,w,h} global points to zoom toward. |
session_id | string | — |
Parameters from the server's own tool schema.
Why record_marker is rated Medium
The tool writes a marker/annotation into an existing recording timeline. This is a reversible write operation (adding metadata/markers to a recording session). It does not delete data, execute code, or involve financial transactions. Severity is low as it only adds annotation markers to a recording.
From the tool's definition Drops a named marker into the active recording's timeline... note becomes a caption source
Attacks that exploit this kind of access
The rule that runs record_marker 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 record_marker, this is the rule to start with:
record_marker stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every record_marker call is checked against it from then on.
Questions about record_marker
Drops a named marker into the active recording's timeline. t_ms is elapsed ms since recording start. Provide bounds (global points, top-left) to zoom toward an element, or omit for full-frame. note becomes a caption source. Returns no_active_session if nothing is recording. It is categorised as a Write tool in the Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
record_marker accepts 4 parameters: name, note, bounds, session_id. Required: name. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for record_marker: 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.
record_marker is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_marker 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.
Set action: deny in the PolicyLayer policy for record_marker. 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.
record_marker 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.
More on Local, and thousands of servers like it.
This server
Across the catalogue