📱 Check Instagram DMs - Demo practice claims only
AI agents call check_instagram_dms to retrieve information from Sassy Fact Check Bot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries Instagram direct messages for the purpose of fact-checking claims. It performs no creation, modification, deletion, or execution of external commands—it simply reads incoming messages. The demo-only nature and focus on 'checking' (not sending, deleting, or modifying) confirms this is a Read category tool.
From the tool's definition Tool name 'check_instagram_dms' and description 'Check Instagram DMs - Demo practice claims only' indicate retrieval of messages without modification. The 'Demo practice claims only' qualifier further limits scope to read-only demonstration data.
Attacks that exploit this kind of access
📱 Check Instagram DMs - Demo practice claims only. It is categorised as a Read tool in the Sassy Fact Check Bot MCP Server, which means it retrieves data without modifying state.
Register the Sassy Fact Check Bot MCP server in PolicyLayer and add a rule for check_instagram_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 Sassy Fact Check Bot. Nothing to install.
check_instagram_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 check_instagram_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 check_instagram_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.
check_instagram_dms is provided by the Sassy Fact Check Bot MCP server (sangreal-007/sassy-factcheck-bot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →