List recent stored MCP results so a client can choose a result_id for export or follow-up.
AI agents call list_results to retrieve information from Instagram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of previously stored results. It performs a passive retrieval with no side effects, no data modification, and no execution of external operations. The user can then choose a result_id for subsequent actions (export, follow-up), but the list_results tool itself only reads and presents information. This is a clear Read operation with low severity and negligible blast radius.
From the tool's definition Tool description states 'List recent stored MCP results' — a retrieval operation with no modification, deletion, or execution capability. The action is to display stored data for selection purposes only.
Documented attack patterns abuse exactly the kind of access list_results gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Instagram, and nothing reaches the server without passing your rules. This is the rule we recommend for list_results:
{
"version": "1",
"default": "deny",
"tools": {
"list_results": {}
}
}list_results 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.
List recent stored MCP results so a client can choose a result_id for export or follow-up. It is categorised as a Read tool in the Instagram MCP Server, which means it retrieves data without modifying state.
Register the Instagram MCP server in PolicyLayer and add a rule for list_results: 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 Instagram. Nothing to install.
list_results 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 list_results 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 list_results. 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.
list_results is provided by the Instagram MCP server (lupikovoleg/instagram-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Instagram, 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.
43 Instagram tools catalogued and risk-classified — across an index of 43,000+ MCP servers.