Fetch content from any URL and convert to HTML format
AI agents call fetch-html to retrieve information from MCP URL Fetcher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and processes web content for consumption by the LLM. It performs no writes, deletes, code execution, or financial operations. The only potential concern is that fetching arbitrary URLs could expose sensitive content if an attacker controls the URL parameter, but the tool itself is not the vector — it is a straightforward Read operation.
From the tool's definition Tool description states 'Fetch content from any URL and convert to HTML format' — the verb 'fetch' and 'convert' indicate data retrieval with no modification or destructive action.
Attacks that exploit this kind of access
Fetch content from any URL and convert to HTML format. It is categorised as a Read tool in the MCP URL Fetcher MCP Server, which means it retrieves data without modifying state.
Register the MCP URL Fetcher MCP server in PolicyLayer and add a rule for fetch-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 URL Fetcher. Nothing to install.
fetch-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 fetch-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 fetch-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.
fetch-html is provided by the MCP URL Fetcher MCP server (nathanonn/mcp-url-fetcher). 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 →