n8n

The built-in app node reference enumerates several hundred individually documented nodes spanning CRM, marketing, ITSM, HR, databases, warehouses, cloud infrastructure, storage, messaging, security and finance, with major nodes such as Gmail, Google Drive, Google Sheets, Postgres and OpenAI carrying separate pages per operation family.

Core nodes add HTTP Request, GraphQL, SSH, Execute Command and Code for anything uncatalogued, community and custom nodes extend the set further, and the MCP Client node connects agents to external MCP servers. Sub-workflows and app nodes can be exposed to agents as tools.

Sourcedocs.n8n.io app nodes, core nodes, MCP Client and how tools work pagesread 2026-08-31

Flow logic is documented across split with conditionals using If and Switch, merge data, loop, wait, handle errors gracefully, and understand execution order for multi-branch workflows.

Breaking workflows into smaller parts documents calling workflows from other workflows, and converting nodes to a sub-workflow automatically includes attached AI sub-nodes such as chat models and memory.

Agent nodes act as root nodes orchestrating typed sub-node connections for language models, tools, memory and output parsers, and sub-workflows can be attached to an agent as tools. Canvas groups, sticky notes and workflow tags support organizing large workflows.

Sourcedocs.n8n.io flow logic tree, break workflows into smaller parts, convert to sub-workflows and how tools work pagesread 2026-08-31

A dedicated AI concepts section documents storing and searching data with vectors, covering vector databases, embeddings, retrievers and document loaders, alongside a page on retrieving relevant context that explains retrieval-augmented generation and how to use it in n8n.

Vector store providers attach as sub-nodes so the index can be held in a customer-run database, and a worked example documents scraping website content into Pinecone and querying it from a chat workflow. Data tables provide structured tabular data management within project boundaries, and Default Data Loader and text splitter components handle ingestion.

Sourcedocs.n8n.io store and search data with vectors, retrieve relevant context, use website content and data tables pagesread 2026-08-31

A documented pattern requires human approval before an AI Agent executes specific tools, and a separate pattern sets a human fallback that triggers a human answer when the AI cannot help. A dedicated Guardrails node ships as a core node for policy enforcement on AI workflows. Workflow reviews allow submitting a version for review before publishing, comparing changes with a visual diff, discussing in activity comments, and approving or requesting changes. Wait and Stop And Error nodes provide pause and halt primitives, and workflow publishing is a distinct step from saving.

Sourcedocs.n8n.io human-in-the-loop for tools, set a human fallback, Guardrails node, workflow reviews and save and publish pagesread 2026-08-31

The vendor's security page states n8n undergoes continuous evaluation and annual audits by an independent auditor against SOC 2, that its SOC 2 report is available to enterprise customers and a SOC 3 report is published for everyone else, and that third-party penetration tests of the production environment run at least once a year.

The same page states SSO, SAML and LDAP on the Enterprise plan and advanced RBAC on all paid plans. The documentation's security configuration tree adds SAML and OIDC single sign-on, MFA enforcement, a self-service security audit, node blocking, task runner hardening, SSRF protection, encryption key rotation, JWE decryption of OAuth tokens and execution data redaction.

Sourcen8n.io legal security page, docs.n8n.io security configuration treeread 2026-09-29

Executions are documented as first-class objects with pages for viewing all executions, viewing executions for a single workflow, customizing execution data so runs can be filtered by custom fields, and debugging by copying prior execution data into the canvas.

Tracing workflow and node executions to an OpenTelemetry collector is documented, alongside Prometheus metrics, visualizing metrics with Grafana, log configuration and an insights metrics layer.

Workflow change history and version restore are documented separately, execution data can be redacted for compliance, and a LangChain in n8n page documents connecting a self-hosted instance to LangSmith for tracing.

Sourcedocs.n8n.io understand executions, trace executions with OpenTelemetry, monitor n8n, view change history and LangChain in n8n pagesread 2026-08-31

The Tools Agent documentation states that a memory sub-node lets users hold an ongoing conversation across multiple queries but that memory does not persist between sessions, and the default Simple Memory node, previously named Window Buffer Memory, is a bounded buffer.

Memory attaches to agents as a typed AiMemory sub-node, with session IDs resolved from input data or a custom key and optionally scoped per node so separate memory nodes in one workflow do not share history. External chat memory backends can be attached in place of the simple buffer, and Data tables provide structured storage across runs. A dedicated How memory works concept page documents the model.

Sourcedocs.n8n.io Tools Agent, how memory works, AI Agent common issues and data tables pagesread 2026-08-31

Install options document one-line setup, Docker, Docker Compose, npm and deployment to DigitalOcean, Heroku, Hetzner, AWS, Azure, Google Cloud Run, Google Kubernetes and OpenShift Local, alongside managed n8n Cloud. An isolate n8n configuration example documents preventing the instance from connecting with n8n's servers.

The database is customer-chosen, external storage is documented for binary and execution data, queue mode and task runners cover scaling, and an OEM deployment path documents surfacing n8n inside another product. Editions are compared across Community, Registered Community, Business and Enterprise.

Sourcedocs.n8n.io install options, isolate n8n, choose n8n's database, scaling and compare editions pagesread 2026-08-31

Using templates is documented as one of the named ways of building workflows, alongside a configuration option for self-hosted instances to point at a custom workflow templates library. A curated self-hosted AI Starter Kit is documented as providing a list of AI elements to quickly start building AI workflows. Individual node pages link to browsable template collections for that node, and.n8np packages bundle workflows, folders or whole projects with their dependencies into a portable file for transfer between instances. Learning paths provide interactive courses building real workflows.

Sourcedocs.n8n.io use templates, configure a custom workflow templates library, deploy with the AI starter kit and n8n packages pagesread 2026-08-31

Documented trigger nodes include Schedule Trigger, Webhook, Chat Trigger, Email Trigger over IMAP, RSS Feed Trigger, Local File Trigger, SSE Trigger, n8n Form Trigger, Error Trigger, Activation Trigger, Workflow Trigger, Execute Sub-workflow Trigger, n8n Trigger, Evaluation Trigger, MCP Server Trigger and Microsoft Agent 365 Trigger.

A durable scheduler is documented as running time-based workflows from a database-backed queue on self-hosted instances. Agents are documented as publishable so people reach them through chat, channels and schedules, and a Respond to Webhook node plus streaming responses complete the request-response surface.

Sourcedocs.n8n.io core node reference, durable scheduler, build and manage agents and stream real-time responses pagesread 2026-08-31

The AI Agent node requires a connected Chat Model sub-node and errors without one, with the documentation describing clicking the Chat Model connector to open a selection of possible chat models. Models attach as sub-nodes so different agents and chains in one workflow can use different models.

Documented first-class model provider nodes include OpenAI, Anthropic, Google Gemini, Mistral AI, Perplexity, Qwen Cloud, MiniMax and Moonshot Kimi, and the self-hosted AI starter kit documents running local models alongside n8n. A LangChain in n8n page documents the underlying abstraction and LangSmith connection.

Sourcedocs.n8n.io AI Agent node and common issues, what agents do, app node reference and AI starter kitread 2026-08-31

The MCP Server Trigger node is documented as allowing n8n to act as a Model Context Protocol server, making n8n tools and workflows available to MCP clients over SSE or streamable HTTP, with a separate page on building and running n8n workflows from MCP clients and admin oversight of connected MCP clients including consent revocation. A public REST API is documented, including instructions for disabling it.

Custom and community nodes extend the catalog, npm modules can be enabled in the Code node, and.n8np packages export workflows, folders or whole projects as portable files with a manifest, size limits and API key scopes. An OEM deployment path documents embedding n8n in another product using OAuth 2.0 token exchange, iframe SSO and delegated API access.

Sourcedocs.n8n.io MCP Server Trigger, connect to n8n MCP server, n8n packages, security and OEM deployment pagesread 2026-08-31

Dedicated Evaluation and Evaluation Trigger core nodes ship with the platform, supported by a four-page Test and improve AI workflows documentation section covering why to test, running quick evaluations during development against known test cases, using metric-based evaluations to measure, score and improve production workflow performance over time, and fixing common issues. Debugging is separately documented through pin and mock data, debug executions which copy earlier execution data into the current workflow, types of executions including manual and partial runs, and dirty node tracking.

Sourcedocs.n8n.io test and improve AI workflows section, Evaluation and Evaluation Trigger nodes, understand executions pagesread 2026-08-31

n8n ships an Airtop app node, documented as controlling a cloud-based web browser for querying, scraping and interacting with web pages, with operations to manage browser sessions and windows and to click an element, fill a form, hover, scroll and type, authenticated with Airtop credentials. That is a third-party browser engine wired in through a node rather than a browser the platform ships; no browser, desktop or computer-use node of n8n's own appears among the core nodes, and SSH and Execute Command run commands on remote hosts rather than operating a rendered interface.

Sourcedocs.n8n.io Airtop node pageread 2026-09-29