Fetch URL, convert to markdown, index in FTS5, and optionally search. Caches 24h - same URL returns cached results instantly. WORKFLOW: Fetch once with queries to get relevant content immediately. If queries don
AI agents call mcx_fetch to retrieve information from MCX (Modular Code Execution) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though mcx_fetch only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Documented attack patterns abuse exactly the kind of access mcx_fetch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCX (Modular Code Execution), and nothing reaches the server without passing your rules. This is the rule we recommend for mcx_fetch:
{
"version": "1",
"default": "deny",
"tools": {
"mcx_fetch": {}
}
}mcx_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.
Fetch URL, convert to markdown, index in FTS5, and optionally search. Caches 24h - same URL returns cached results instantly. WORKFLOW: Fetch once with queries to get relevant content immediately. If queries don. It is categorised as a Read tool in the MCX (Modular Code Execution) MCP Server, which means it retrieves data without modifying state.
Register the MCX (Modular Code Execution) MCP server in PolicyLayer and add a rule for mcx_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 MCX (Modular Code Execution). Nothing to install.
mcx_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 mcx_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 mcx_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.
mcx_fetch is provided by the MCX (Modular Code Execution) MCP server (schizoidcock/mcx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 MCX (Modular Code Execution) tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 MCX (Modular Code Execution) tools catalogued and risk-classified — across an index of 42,500+ MCP servers.