AI agents call read_dms to retrieve information from Instagram DM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/queries existing Instagram direct messages from the user's inbox. It has no capability to modify, delete, send, or execute any actions—it is purely data retrieval. The low severity reflects minimal blast radius: accidental access to an account's DMs is less dangerous than the ability to send messages or delete data. Confidence is high because the intent is unambiguous.
From the tool's definition Tool name 'read_dms' and description 'Read recent Instagram DMs from the inbox' explicitly perform retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access read_dms gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Instagram DM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_dms:
{
"version": "1",
"default": "deny",
"tools": {
"read_dms": {}
}
}read_dms 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.
Read recent Instagram DMs from the inbox. It is categorised as a Read tool in the Instagram DM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Instagram DM MCP Server MCP server in PolicyLayer and add a rule for read_dms: 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 DM MCP Server. Nothing to install.
read_dms 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 read_dms 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 read_dms. 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.
read_dms is provided by the Instagram DM MCP Server MCP server (taskmaster-ai/insta-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Instagram DM MCP Server, 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.
3 Instagram DM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.