AI agents call list_workflow_nodes 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.
The tool retrieves or lists workflow node information with no side effects or modifications. Despite the empty description reducing confidence slightly, the naming convention clearly indicates a read-only query operation typical of inspection/enumeration tools. This poses minimal risk as it only exposes information about workflow structure.
From the tool's definition Tool name 'list_workflow_nodes' indicates a retrieval/query operation. The sibling context shows this server manipulates Dify workflow DSL definitions. A 'list' operation retrieves and enumerates existing nodes without modifying state.
Attacks that exploit this kind of access
list_workflow_nodes. 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 list_workflow_nodes: 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.
list_workflow_nodes 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_workflow_nodes 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_workflow_nodes. 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_workflow_nodes 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 →