AI agents call proxy_direction to retrieve information from Open Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit description, confidence is moderate. The tool name and server context suggest this retrieves directional data about shareholder proxy voting or AGM governance matters—a read-only query operation. No evidence of modification, deletion, execution, or financial impact. Classified as Read due to the informational nature of proxy/governance data access tools in this domain.
From the tool's definition Tool name 'proxy_direction' with empty description. Based on naming context alongside sibling tools (agm_agenda_xml, agm_aoi_change_xml, etc.), this appears to be a data retrieval tool for AGM/governance disclosures, consistent with server's stated purpose to…
Documented attack patterns abuse exactly the kind of access proxy_direction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Open Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for proxy_direction:
{
"version": "1",
"default": "deny",
"tools": {
"proxy_direction": {}
}
}proxy_direction 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.
proxy_direction. It is categorised as a Read tool in the Open Proxy MCP Server, which means it retrieves data without modifying state.
Register the Open Proxy MCP server in PolicyLayer and add a rule for proxy_direction: 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 Open Proxy. Nothing to install.
proxy_direction 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 proxy_direction 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 proxy_direction. 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.
proxy_direction is provided by the Open Proxy MCP server (marcoyou/open-proxy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Open Proxy, 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.
54 Open Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.