Capture a screenshot of any URL and return it as a base64-encoded image. Price: $0.01 USDC per capture (paid mode) | Free test: example.com, example.org, httpbin.org only. Without X402_PRIVATE_KEY, only test domains are available. With a wallet key, any URL can be captured via the paid endpoint. ...
AI agents call x402_screenshot to retrieve information from x402 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns screenshot data, which is fundamentally a read operation with no side effects on the target system. However, severity is elevated to 'medium' rather than 'low' because: (1) screenshots can capture sensitive information displayed on web pages (credentials, private data, confidential documents), (2) the tool enables reconnaissance of arbitrary URLs when a wallet key is provided, and (3)…
From the tool's definition Tool description states 'Capture a screenshot of any URL and return it as a base64-encoded image.' This is a read operation that retrieves visual data without modifying or deleting any underlying resources.
Attacks that exploit this kind of access
Capture a screenshot of any URL and return it as a base64-encoded image. Price: $0.01 USDC per capture (paid mode) | Free test: example.com, example.org, httpbin.org only. Without X402_PRIVATE_KEY, only test domains are available. With a wallet key, any URL can be captured via the paid endpoint. Returns: base64 PNG/JPEG/WebP image data. It is categorised as a Read tool in the x402 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the x402 MCP Server MCP server in PolicyLayer and add a rule for x402_screenshot: 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 x402 MCP Server. Nothing to install.
x402_screenshot 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 x402_screenshot 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 x402_screenshot. 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.
x402_screenshot is provided by the x402 MCP Server MCP server (jameswilliamwisdom/x402-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 →