Render provided HTML into a screenshot via PagePixels /snap_html (JSON response).
AI agents invoke snap_html to trigger actions in PagePixels Screenshots MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a browser rendering operation on provided HTML content, triggering an external service to process and render arbitrary HTML. It is not a simple read operation — it submits content to an external API that executes rendering. Since arbitrary HTML (including scripts) could be submitted, it constitutes an Execute-level action.
From the tool's definition Render provided HTML into a screenshot via PagePixels /snap_html
Attacks that exploit this kind of access
Render provided HTML into a screenshot via PagePixels /snap_html (JSON response). It is categorised as a Execute tool in the PagePixels Screenshots MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PagePixels Screenshots MCP Server MCP server in PolicyLayer and add a rule for snap_html: 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 PagePixels Screenshots MCP Server. Nothing to install.
snap_html is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the snap_html 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 snap_html. 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.
snap_html is provided by the PagePixels Screenshots MCP Server MCP server (pagepixels/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 →