Take a screenshot of a webpage and convert visual layout to structured markdown description. Perfect for agents that need to understand page layout, UI elements, or visual content when text extraction is insufficient.
Accepts URL/endpoint input (url)
Part of the Web Content Extractor MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call screenshot_to_markdown to retrieve information from Web Content Extractor without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though screenshot_to_markdown only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
screenshot_to_markdown:
rules:
- action: allowSee the full Web Content Extractor policy for all 5 tools.
Agents calling read-class tools like screenshot_to_markdown have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Take a screenshot of a webpage and convert visual layout to structured markdown description. Perfect for agents that need to understand page layout, UI elements, or visual content when text extraction is insufficient.. It is categorised as a Read tool in the Web Content Extractor MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for screenshot_to_markdown. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Web Content Extractor MCP server.
screenshot_to_markdown 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 screenshot_to_markdown rule in your Intercept 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 Intercept policy for screenshot_to_markdown. 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.
screenshot_to_markdown is provided by the Web Content Extractor MCP server (@agenson-horrowitz/web-content-extractor-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept