How do I add Glen to an n8n workflow?

Glen is a standard remote MCP server. Add it as an MCP tool/credential in n8n, then call it from an AI Agent node to retrieve context and record observations in a single step.

Does every workflow share the same memory?

Yes. Glen is org-scoped, so every workflow in your instance, and every other MCP client your team uses, reads from and writes to the same store.

Shared memory for n8n builders

If you build automations in n8n, you already chain together dozens of nodes, HTTP calls, AI steps, branches, that move data between systems and make decisions along the way. But each workflow execution starts fresh. The AI nodes in your flows have no memory of what previous runs learned, no shared context about a customer or an account, no durable record of the decisions your automations already made. You end up bolting on a database node, a vector store, or a spreadsheet just to give your flows something to remember, and every workflow reinvents that wheel. Glen, shared memory for AI agents, gives your n8n workflows one durable, org-shared memory layer they all read from and write to through a single MCP tool.

Connect Glen to n8n as an MCP tool and any workflow can both retrieve relevant context and record what it learned in one call. An AI Agent node handling an inbound support ticket can pull everything the organization already knows about that customer before drafting a reply; a node at the end of the flow can write back the resolution so the next workflow, days later, starts informed. You stop maintaining a side database and a manual write path just to give your automations a memory, and you stop letting each flow operate in its own silo.

Because Glen is org-scoped, the memory is shared across every workflow in your n8n instance and across every other tool your team uses. A lead-enrichment flow learns a durable fact about an account; a separate outreach flow reads it next time. The sales workflow and the support workflow draw on the same knowledge instead of each rediscovering it. And because Glen is a standard MCP server, the same memory your n8n flows write is readable from Claude, Cursor, or any other MCP client, so the automations you run unattended and the work your team does by hand compound into one store. You wire it in once over OAuth or an API key and let the memory grow run after run. For builders who already think in nodes and triggers, Glen is just one more node, except this one remembers everything.

FAQ

How do I add Glen to an n8n workflow?: Glen is a standard remote MCP server. Add it as an MCP tool/credential in n8n, then call it from an AI Agent node to retrieve context and record observations in a single step.
Does every workflow share the same memory?: Yes. Glen is org-scoped, so every workflow in your instance, and every other MCP client your team uses, reads from and writes to the same store.