AI agents call get_supported_app_modes to retrieve information from Dify MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns information about supported application modes in Dify. It has no side effects, performs no modifications, executes no external operations, and does not access sensitive data. It is a simple informational read operation with minimal risk if called by an AI agent.
From the tool's definition Tool name 'get_supported_app_modes' and description 'Get the list of supported Dify app modes' indicate a query/retrieval operation that returns configuration information without modifying state.
Attacks that exploit this kind of access
Get the list of supported Dify app modes. It is categorised as a Read tool in the Dify MCP MCP Server, which means it retrieves data without modifying state.
Register the Dify MCP server in PolicyLayer and add a rule for get_supported_app_modes: 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 Dify MCP. Nothing to install.
get_supported_app_modes 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 get_supported_app_modes 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 get_supported_app_modes. 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.
get_supported_app_modes is provided by the Dify MCP server (taiki-kuraishi/dify-mcp). 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 →