Capture an accessibility snapshot of the current tab (ARIA tree, landmarks, headings, ref map). Returns: (1) YAML snapshot text (with ref map), (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs overlaid. Default detail='shorten' for optimized output. Use detail='all' for complete sna...
AI agents call browser_snapshot to retrieve information from Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
detail | string | — | Snapshot detail level. Default: shorten. Use "all" for no limits. Result includes snapshot text, plain screenshot, and screenshot with refs using same snapshotI |
fullPage | boolean | — | Capture full page (true) or only viewport-visible content (false). Default: true |
Parameters from the server's own tool schema.
browser_snapshot is a pure read operation that captures the current state of a webpage through accessibility snapshots and screenshots. It has no side effects on the browser state, data, or external systems. The tool merely retrieves and returns visual/structural information about the current tab. This is consistent with Read category tools like 'get' and 'fetch'.
From the tool's definition Tool description states it 'Capture[s] an accessibility snapshot' and 'Returns: (1) YAML snapshot text, (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs overlaid.' The parameters detail and fullPage control verbosity and scope of the read…
Attacks that exploit this kind of access
Capture an accessibility snapshot of the current tab (ARIA tree, landmarks, headings, ref map). Returns: (1) YAML snapshot text (with ref map), (2) base64 PNG screenshot, (3) base64 PNG screenshot with refs overlaid. Default detail='shorten' for optimized output. Use detail='all' for complete snapshot when you see elements in the screenshot without refs in the snapshot. Use fullPage=false for viewport-only. It is categorised as a Read tool in the Search MCP Server, which means it retrieves data without modifying state.
browser_snapshot accepts 2 parameters: detail, fullPage. The full parameter table on this page comes from the server's own tool schema.
Register the Search MCP server in PolicyLayer and add a rule for browser_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 Search. Nothing to install.
browser_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 browser_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 browser_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.
browser_snapshot is provided by the Search MCP server (search-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 →