capture_timeline
AI agents call capture_timeline to retrieve information from Screen MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool captures timeline data from screen recordings, which is a read operation—it retrieves visual information without side effects. However, the severity is high because timeline/screenshot capture can expose sensitive information (passwords, PII, proprietary content, authentication tokens) visible on screen, creating significant privacy and security risk if misused by an agent.
From the tool's definition Tool name 'capture_timeline' combined with sibling tools 'start_timeline_capture', 'get_timeline_chunk', and 'get_timeline_manifest' indicates this reads/retrieves screen recording timeline data.
Attacks that exploit this kind of access
capture_timeline. It is categorised as a Read tool in the Screen MCP MCP Server, which means it retrieves data without modifying state.
Register the Screen MCP server in PolicyLayer and add a rule for capture_timeline: 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 Screen MCP. Nothing to install.
capture_timeline is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the capture_timeline 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 capture_timeline. 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.
capture_timeline is provided by the Screen MCP server (jeandelest/screen-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →