AI agents call agm_items 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.
The tool operates within a governance data platform serving investors with read-only access to Korean stock AGM disclosures. The naming pattern and context of sibling tools (all prefixed 'agm_' and focused on parsing/retrieving governance documents) indicates this retrieves or queries AGM-related items without modification, deletion, or execution of arbitrary code.
From the tool's definition Tool name 'agm_items' combined with sibling tools that all retrieve AGM (Annual General Meeting) governance disclosures (agm_agenda_xml, agm_aoi_change_xml, agm_capital_reserve_xml, etc.) suggests data retrieval.
Documented attack patterns abuse exactly the kind of access agm_items 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 agm_items:
{
"version": "1",
"default": "deny",
"tools": {
"agm_items": {}
}
}agm_items 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.
agm_items. 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 agm_items: 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.
agm_items 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 agm_items 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 agm_items. 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.
agm_items 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.