Fetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete.
AI agents call get-rendered-html to retrieve information from MCP Server Fetch Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and fetches web content (rendered HTML) with no side effects. It is a read-only operation that queries remote web pages and returns their content. While it uses a headless browser to execute JavaScript, the purpose is data retrieval only, not executing arbitrary code or triggering external operations with variable effects. No data is modified, deleted, or created on the target system.
From the tool's definition Tool name 'get-rendered-html' and description 'Fetches fully rendered HTML content' indicate data retrieval. The description explicitly states it is for fetching content and does not describe any modifications, deletions, or financial operations.
Documented attack patterns abuse exactly the kind of access get-rendered-html gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server Fetch Python, and nothing reaches the server without passing your rules. This is the rule we recommend for get-rendered-html:
{
"version": "1",
"default": "deny",
"tools": {
"get-rendered-html": {}
}
}get-rendered-html is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Fetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete. It is categorised as a Read tool in the MCP Server Fetch Python MCP Server, which means it retrieves data without modifying state.
Register the MCP Server Fetch Python MCP server in PolicyLayer and add a rule for get-rendered-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 MCP Server Fetch Python. Nothing to install.
get-rendered-html 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 get-rendered-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 get-rendered-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.
get-rendered-html is provided by the MCP Server Fetch Python MCP server (tatn/mcp-server-fetch-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server Fetch Python, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 MCP Server Fetch Python tools catalogued and risk-classified — across an index of 43,000+ MCP servers.