Extract a specific HTML fragment from a webpage using CSS selectors
AI agents call extract-html-fragment to retrieve information from MCP Node Fetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations on web content. It extracts and retrieves HTML fragments using CSS selectors but does not create, modify, delete, or execute code. The operation has minimal blast radius as it only retrieves existing data. No side effects or data mutations are possible.
From the tool's definition Tool description states 'Extract a specific HTML fragment from a webpage using CSS selectors' - this is a retrieval operation with no modification capability. It parses and selects existing content from a webpage without altering data.
Documented attack patterns abuse exactly the kind of access extract-html-fragment gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Node Fetch, and nothing reaches the server without passing your rules. This is the rule we recommend for extract-html-fragment:
{
"version": "1",
"default": "deny",
"tools": {
"extract-html-fragment": {}
}
}extract-html-fragment 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.
Extract a specific HTML fragment from a webpage using CSS selectors. It is categorised as a Read tool in the MCP Node Fetch MCP Server, which means it retrieves data without modifying state.
Register the MCP Node Fetch MCP server in PolicyLayer and add a rule for extract-html-fragment: 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 Node Fetch. Nothing to install.
extract-html-fragment 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 extract-html-fragment 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 extract-html-fragment. 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.
extract-html-fragment is provided by the MCP Node Fetch MCP server (mcollina/mcp-node-fetch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Node Fetch, 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.
3 MCP Node Fetch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.