Page snapshot from a11y tree. Each interactive element gets a ref (e.g. @e1). Use ref in click, fill, hover, etc. Options: interactive (interactive only), compact (remove structural noise), maxDepth (limit depth).
AI agents call take_snapshot to retrieve information from Electron without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays page state via the a11y tree—a read-only query operation with filtering options (interactive, compact, maxDepth). While it runs within an Electron context via CDP, it performs introspection only. The references returned are meant for subsequent tool use (click, fill, hover), but the snapshot operation itself is purely informational with no side effects.
From the tool's definition Tool takes a 'page snapshot' from accessibility tree and returns references to interactive elements. The description explicitly states it is for reading/querying page structure ('Each interactive element gets a ref').
Attacks that exploit this kind of access
Page snapshot from a11y tree. Each interactive element gets a ref (e.g. @e1). Use ref in click, fill, hover, etc. Options: interactive (interactive only), compact (remove structural noise), maxDepth (limit depth). It is categorised as a Read tool in the Electron MCP Server, which means it retrieves data without modifying state.
Register the Electron MCP server in PolicyLayer and add a rule for take_snapshot: 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 Electron. Nothing to install.
take_snapshot 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 take_snapshot 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 take_snapshot. 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.
take_snapshot is provided by the Electron MCP server (ohah/electron-mcp-server). 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 →