AI agents use add_llm_node to create or update resources in Dify MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dify MCP environment.
This tool creates or modifies workflow structure by adding an LLM node, which is a reversible write operation. It does not execute arbitrary code, delete data, or move funds. While it affects workflow behavior, the changes are made to workflow definitions (DSL YAML) and can be undone.
From the tool's definition Tool name 'add_llm_node' with sibling tools 'add_answer_node', 'add_edge', 'add_start_node' indicate data structure modification operations within Dify workflow DSL. The tool adds a node component to a workflow, creating or modifying workflow configuration.
Attacks that exploit this kind of access
add_llm_node. It is categorised as a Write tool in the Dify MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Dify MCP server in PolicyLayer and add a rule for add_llm_node: 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.
add_llm_node is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_llm_node 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 add_llm_node. 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.
add_llm_node 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 →