AI Agent tool execution
The n8n AI Agent node, used inside n8n workflows, determines which attached tool to use for a task and invokes it. Tools include integration nodes exposed as AI tools, Call n8n Workflow Tool, Custom Code Tool, HTTP Request Tool, AI Agent Tool, MCP Client Tool and search/vector-store tools. Excludes the standalone n8n Agents feature (Preview), AI Workflow Builder and the instance-level n8n MCP server.
Recorded characteristics
- Function
- n8n documents the AI Agent node as able to "understand the capabilities of different tools and determine which tool to use depending on the task"; at least one tool sub-node must be connected. The Tools Agent implements LangChain's tool-calling interface, describing available tools and their schemas to the model. n8n distinguishes the Agent node, which "makes decisions about what tools to use", from the Basic LLM Chain, which "doesn't support memory or tools". Agent-type consolidation: the agent-type setting is deprecated from n8n 1.82.0 and all AI Agent nodes now work as a Tools Agent; the Conversational, OpenAI Functions, Plan and Execute, ReAct and SQL agent types are labelled deprecated; the v1 node with the type setting will be removed in n8n 3.0. This is recorded as one capability. Tool surface: built-in integration nodes and a registry of MCP servers connected as tools, Call n8n Workflow Tool ("load any n8n workflow as a tool"), Custom Code Tool, HTTP Request Tool, AI Agent Tool (a root agent calls other agents as tools), MCP Client Tool (AI Agent -> external MCP server), and search/vector-store tools. Call n8n Workflow Tool: the agent can select it, inputs may be model-defined via $fromAI(), and operations in the called workflow use that workflow's own node credentials and configuration. AI-selected parameters: $fromAI() ("Let the model define this parameter") lets the model fill selected tool parameters; it is only available for tools connected to the AI Agent node and does not work with the Code tool. The builder decides which tools are attached, which parameters are model-defined and which remain fixed. Not every tool changes state; many retrieve or compute. The full reasoning-loop detail is not explicitly documented for the workflow-node runtime.
- Data access
- Determined by the tools and credentials attached by the workflow builder (integration nodes, HTTP requests, sub-workflows, MCP servers, vector stores). No data scope beyond configured tools is attributed.
- Actions
- Can take actions
- External actions
- Yes
- Human confirmation
- Conditional
- Permission basis
- Separate permissions
- Administrative control
- Human review for tools: the builder adds a Human review step in the AI Agent's Tools Panel and selects an approval channel (documented: Slack, Discord, Telegram, Microsoft Teams, Gmail, WhatsApp Business Cloud, Google Chat, Microsoft Outlook, n8n Chat). Review can apply to all tools connected to an AI Agent or to selected individual tools. When the agent decides to use a reviewed tool, the workflow pauses before execution and sends a request showing which tool the AI wants to use and with what parameters. Approve: the tool executes with the AI-specified input. Deny: the action is canceled and does not run, and the AI is informed of the rejection. Tools without review execute automatically. Human fallback (routing to a human when the AI cannot answer) is a separate pattern and is not pre-execution approval. Credential and sharing controls: tools use credentials configured in n8n and attached to the node by the builder; credentials can be shared with users or projects (users of a shared credential cannot view or edit its details); workflow sharing allows editors to use all credentials used in the workflow, including credentials not explicitly shared with them. Triggers: the node runs within workflows started by chat, webhook, schedule, application events or other workflows; trigger differences are kept within this capability.
- Default state
- Conditional
- Availability
- Actions require configuration: creating a workflow, adding the AI Agent node, configuring a chat model and its credential, attaching tools with their credentials and descriptions, optionally exposing parameters via $fromAI(), adding a trigger, publishing/activating the workflow, and optionally adding human review. Access to n8n does not give an AI Agent authority to act. The AI Agent node is current; no Preview label applies to it. The standalone n8n Agents feature is in Preview and excluded. No GA date is recorded.
- Licensing
- No separate AI Agent SKU is recorded. Credential sharing is available on n8n Cloud (all plans) and self-hosted Business and Enterprise. Plan details are not inferred beyond the documentation.
- External model or provider
- No single model or provider. The AI Agent uses a customer-selected chat model sub-node from multiple providers (for example OpenAI, Anthropic, Azure OpenAI, Groq, Mistral). The AI Agent Tool documents an optional fallback model used if the primary model fails or is unavailable.
- Limitations and uncertainty
- Permission basis is recorded as separate_permissions: AI Agent tools execute using credentials stored/configured in n8n and attached to the relevant tool or workflow node by the workflow builder. These credentials may belong to or be shared by different users/projects; sharing a credential does not by itself make the record mixed. Invoking-user passthrough is not established (not user_permissions); the agent has no established external identity of its own (not dedicated_agent_identity); multiple authentication methods do not make it mixed. Unresolved: no single reproduced worked example of a specific AI Agent-node external write (classification rests on n8n's documented action classes: sending messages, modifying records, deleting data, external communications, purchases); full reasoning-loop detail is not explicit for the workflow-node runtime; human-review behaviour across every unattended trigger is not established; end-user credential behaviour with AI Agent tools is not established; Chat Hub Personal Agent tool behaviour is not established; standalone n8n Agents (Preview) are excluded and kept as a future candidate; the instance-level n8n MCP server (external client -> n8n workflow) is excluded and kept as a possible future candidate; AI Workflow Builder is design-time and excluded; no GA date established.
Evidence
- AI Agent node
Supports: Function · Availability · Primary source
AI Agent determines which tool to use depending on the task; at least one tool must be connected.
Agent-type setting deprecated from n8n 1.82.0; all AI Agent nodes work as Tools Agent; v1 removed in n8n 3.0; legacy types deprecated.
- Tools Agent
Supports: Function · External model · Primary source
Tools Agent implements LangChain tool calling, describing tools and schemas to the model.
Supports multiple chat model providers (OpenAI, Anthropic, Azure OpenAI, Groq, Mistral, others).
- Agents vs chains
Supports: Function · Primary source
Agent node makes decisions about what tools to use; Basic LLM Chain does not support memory or tools.
- How tools work
Supports: Actions · Primary source
Tool surface: built-in nodes, MCP server registry, Call n8n Workflow Tool, Custom Code Tool, HTTP Request Tool.
- Human-in-the-loop for tools
Supports: Human confirmation · Actions · External actions · Primary source
Human review per tool or all tools; pauses before execution; Approve runs with AI input; Deny cancels, tool does not run, AI informed.
Higher-risk tools such as sending messages, modifying records, or deleting data.
Irreversible actions: deleting data, sending external communications, making purchases.
- Use AI for parameters
Supports: Function · Primary source
$fromAI() lets the model fill selected tool parameters; only for tools connected to the AI Agent; not Code tool.
- Set a human fallback for AI workflows
Supports: Limitations · Primary source
Human fallback routes to a human when the AI cannot answer; distinct from pre-execution approval.
- Workflow sharing
Supports: Permission basis · Primary source
Workflow sharing allows editors to use all credentials used in the workflow, including ones not explicitly shared with them.
- Credential sharing
Supports: Permission basis · Licensing · Primary source
Credentials shared with users or projects; users of a shared credential cannot view or edit its details.
Credential sharing: n8n Cloud all plans; self-hosted Business and Enterprise.
- MCP Client Tool
Supports: Actions · Permission basis · Primary source
MCP Client Tool connects the AI Agent to an external MCP server as a tool.
MCP Client Tool authenticates with Bearer, header, multiple headers or OAuth2 credentials configured on the node.
- Call n8n Workflow Tool
Supports: Actions · Primary source
Call n8n Workflow Tool invokes a sub-workflow as a tool; inputs may be model-defined via $fromAI().
- AI Agent Tool
Supports: External model · Function · Primary source
Optional fallback model when the primary model fails or is unavailable.
Root agent can call other agents as tools (AI Agent Tool).
- Accessing n8n MCP server
Supports: Limitations · Primary source
Instance-level n8n MCP server lets external clients search, trigger and edit workflows; opposite direction, excluded.
- Use AI Workflow Builder
Supports: Limitations · Primary source
AI Workflow Builder creates/refines/debugs workflows from natural language; design-time, excluded.
- Use Chat Hub
Supports: Limitations · Primary source
Chat Hub is a chat surface for models, personal agents and published workflow agents; not a separate runtime here.
- Build and manage agents
Supports: Limitations · Primary source
Standalone n8n Agents are in Preview with Agent Builder, publish lifecycle, channels and schedules; excluded from this capability.