AI agents call pinchtab_snapshot to retrieve information from Pinchtab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval of page structure and metadata. It returns references to elements that other tools (like pinchtab_click) would then act upon, but the snapshot operation itself has no side effects, creates no data modifications, and triggers no external operations. It is purely informational and defensive—used to understand what elements exist before performing actions.
From the tool's definition Tool description states 'Get an accessibility tree snapshot of the page' and 'Returns element refs' — it retrieves and queries the accessibility tree structure without modifying or executing actions.
Attacks that exploit this kind of access
Get an accessibility tree snapshot of the page. Returns element refs (e0, e1, …) that can be used with click/type/press. Use filter=. It is categorised as a Read tool in the Pinchtab MCP Server, which means it retrieves data without modifying state.
Register the Pinchtab MCP server in PolicyLayer and add a rule for pinchtab_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 Pinchtab. Nothing to install.
pinchtab_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 pinchtab_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 pinchtab_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.
pinchtab_snapshot is provided by the Pinchtab MCP server (maderwin/pinchtab-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 →