Fetches web page content using a real browser and returns cleaned HTML.
AI agents call auth_fetch to retrieve information from Auth Fetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The core function is data retrieval (Read category). However, the medium severity reflects the elevated risk profile: the tool handles authenticated sessions and may expose sensitive data that the user is authorized to access but an AI agent might exfiltrate or misuse. The local storage of browser profiles and credentials increases the blast radius beyond a simple unauthenticated fetch.
From the tool's definition Tool description states it 'Fetches web page content using a real browser and returns cleaned HTML' - this is a retrieval operation with no data modification.
Documented attack patterns abuse exactly the kind of access auth_fetch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Auth Fetch, and nothing reaches the server without passing your rules. This is the rule we recommend for auth_fetch:
{
"version": "1",
"default": "deny",
"tools": {
"auth_fetch": {}
}
}auth_fetch 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 web page content using a real browser and returns cleaned HTML. It is categorised as a Read tool in the Auth Fetch MCP Server, which means it retrieves data without modifying state.
Register the Auth Fetch MCP server in PolicyLayer and add a rule for auth_fetch: 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 Auth Fetch. Nothing to install.
auth_fetch 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 auth_fetch 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 auth_fetch. 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.
auth_fetch is provided by the Auth Fetch MCP server (ymw0407/auth-fetch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Auth Fetch tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Auth Fetch tools catalogued and risk-classified — across an index of 42,500+ MCP servers.