AI agents call fetch_page to retrieve information from Web Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to fetch and read content from a URL, which is a read-only operation with no side effects. The server explicitly mentions 'full-text URL reading' as a capability. While the tool description is empty, the name and server context strongly indicate this retrieves data without modifying or executing anything.
From the tool's definition Tool name 'fetch_page' combined with server description indicating 'full-text URL reading' capability. No description provided for the tool itself, but context from sibling tools (get_github_issue, groq_analyze_page) and server's stated purpose suggests…
Documented attack patterns abuse exactly the kind of access fetch_page gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Web Search MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for fetch_page:
{
"version": "1",
"default": "deny",
"tools": {
"fetch_page": {}
}
}fetch_page 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.
fetch_page. It is categorised as a Read tool in the Web Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Web Search MCP server in PolicyLayer and add a rule for fetch_page: 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 Web Search MCP. Nothing to install.
fetch_page 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_page 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_page. 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_page is provided by the Web Search MCP server (sydasif/web-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Web Search MCP, 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.
15 Web Search MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.