n8n Adds Quick OAuth Connections to 70 MCP Servers and Outlines Workflow Integration Approaches

n8n Adds Quick OAuth Connections to 70 MCP Servers and Outlines Workflow Integration Approaches n8n has introduced quick OAuth connections for nearly 70 Model Context Protocol (MCP) servers directly from the Node panel, while providing guidance on when to use native nodes, agent tools, or full MCP servers within workflows. Users can now connect to 70 MCP servers—including new additions like Airtable, Grafana, Miro, New Relic, Jotform, and PandaDoc—via an OAuth flow, with an MCP Client Tool for custom endpoints. Native nodes are suited for deterministic workflows where API steps, inputs, and error handling must execute consistently without AI decision-making. Adding a node to an AI agent as a tool allows the agent to decide when to trigger a single, predefined action, requiring fewer LLM calls than broader toolsets. MCP servers grant agents an entire suite of tools to decide which actions to take and how to execute them, and workflows can combine nodes, agent tools, and MCP servers together. Streamlined MCP Connections n8n added a batch of MCP servers accessible directly from the Node panel, expanding the list to 70 services with an OAuth configuration. New additions like Airtable, Grafana, Miro, New Relic, Jotform, and PandaDoc join existing options like Notion, Stripe, and GitLab. Instead of requiring manual internal integrations and permission setups, connections are handled via OAuth, with upcoming additions focusing on services supporting OAuth and Dynamic Client Registration (DCR). An MCP Client Tool is also available to configure unlisted endpoints. Choosing Between Nodes, Tools, and MCP Servers Native nodes are designed for deterministic tasks where fixed logic requires no decision-making, ensuring identical behavior and fine-grained control each time. Converting a node into an agent tool enables the agent to decide when to call a specific, predefined action, which limits the required reasoning and reduces LLM calls. In contrast, connecting an MCP server exposes a broad set of tools that allows the agent to autonomously decide what actions to perform and how to carry them out, though individual tools within the server can still be toggled on or off. Combining Integration Models The different connection types are designed to complement rather than replace one another. Workflows can incorporate native nodes for deterministic precision, agent tools for bounded discretion over single actions, and MCP servers when an agent needs a broader capability surface to reason over.

n8n 支持一键连接近 70 个 MCP 服务器，并阐释不同工作流组件的使用场景 n8n 现已支持直接从节点面板通过 OAuth 一键连接近 70 个 MCP 服务器，简化了 AI Agent 与各类服务的集成流程。同时，团队分析了原生节点、Agent 工具与 MCP 服务器的特点，并指导用户如何在不同工作流中选择或组合搭配。 n8n 新增对 Airtable、Grafana、Miro 等近 70 个 MCP 服务器的快速 OAuth 连接支持，未列出的服务可通过 MCP Client Tool 配置。 原生节点适用于无需判断的确定性工作流，提供对输入、输出和错误处理的细粒度控制。 作为 Agent 工具的节点允许模型自主决定调用时机，但执行的操作严格受限，能降低推理负担和 LLM 调用开销。 MCP 服务器为 Agent 提供成套工具集，使其能自主决定使用何种操作，具备高灵活性但也需要模型承担更多推理。 简化 MCP 服务器集成 n8n 在节点面板中推出了近 70 个可通过 OAuth 快速连接的 MCP 服务器，包括新增的 Airtable、Grafana、Miro、New Relic 等，以及此前已支持的 Notion、Stripe 和 GitLab 等。相比过去需要管理员权限、配置内部集成及多种工具操作的繁琐流程，现在仅需点击授权即可让 AI Agent 读取数据、草拟页面或更新数据库。未来还将支持更多具备 OAuth 和 DCR 的服务器；对于未列出的服务，用户亦可使用 MCP Client Tool 手动接入。 原生节点与 Agent 工具的适用场景 原生节点适合具有确定性逻辑的工作流，用户可以精确掌握每次 API 调用的输入、输出和错误处理，适用于如为每位新客户在固定数据库生成页面等无需决策的场景。若将节点作为工具绑定给 AI Agent，Agent 可以根据上下文决定何时调用，但工具的操作内容预先固定，这种明确性能够减少 Agent 的推理复杂度并降低 LLM 调用成本。 MCP 服务器的优势与三者结合 MCP 服务器适用于赋予 Agent 自主探索与决策能力的场景。一次连接即可为 Agent 提供完整的工具集（支持单独开启或关闭特定工具），Agent 能根据需求自主选择搜索、记录或更新等具体行为，这种灵活性依赖于模型更深入的推理。原生节点、Agent 固定工具与 MCP 服务器互不替代，各自承担精确执行、有限裁量和广泛推理的职责，三者可在复杂工作流中混合使用。

The team just rolled out a fresh batch of [MCP servers](https://docs.n8n.io/build/integrate-ai/mcp-servers) you can add straight from the Node panel. New additions like Airtable, Grafana, Miro, New Relic, Jotform, and PandaDoc are joining the ones you could already connect to, like Notion, Stripe, GitLab, Apify, Linear, monday.com, and Hugging Face. Connecting to 70 services (and counting) is now a quick OAuth flow. If you already use any of these day to day, the unlock is pretty immediate. Take Notion, for example. I use it frequently in workflows, but getting it properly wired up to an Agent used to mean reaching out to an admin for the right permissions, creating an internal integration and sharing pages with it, and configuring multiple Notion tools with different operations. Now it's just an OAuth click and an agent can pull meeting notes for context, draft a page from the conversation, and update a database when something happens elsewhere. All of these MCP server connections are similarly simple to set up. Additional connections are on the way, starting with more of the most-used MCP servers that have OAuth and Dynamic Client Registration (DCR). If you need one that’s not yet listed, the [**MCP Client Tool**](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp) lets you point at any MCP endpoint with a bit more setup. **When to reach for a node, an agent tool, or an MCP server?** **Native nodes** are the right call for deterministic workflows. If you know the exact API call you need at a specific step, or you're building something that has to behave the same way every time, a node gives you fine-grained control over inputs, outputs, and error handling. Use nodes wherever the logic doesn't need a decision made. *Example: You want every new customer to get a welcome page in your team wiki. The Notion node creates that page in the same database, with the same fields, every single time. No judgment call needed, so a node is all you need.* When you **add a node to your AI Agent as a tool**, the agent chooses when to call it, but you still define the exact action ahead of time. Because the tool is fixed and well-defined, the agent needs less reasoning to use it correctly, which often means fewer LLM calls than if it had to work out what to do with a broader toolset. *Example: Your support agent has a "Log escalation" Notion tool. It's one specific action, pointed at one specific database. The agent decides when an issue needs escalating, but it can't do anything with Notion beyond that one job.* **MCP servers** shine when you’re letting an agent decide what to do. Connect once, and the agent gets a whole toolset it can pick from as needed. You can still toggle individual tools on or off, so you decide what's exposed, but the agent decides which to use, when, and how. That flexibility comes with more reasoning on the agent's side. *Example: Connect the Notion MCP server and your agent can search pages, pull meeting notes, create a draft, or update a database entry, whichever fits the request it gets. You didn't build a tool for each of those; they came with the connection.* **You don’t have to pick just one** None of these replace the others. Nodes give you precision as a workflow step, agent tools give the agent limited discretion over fixed actions, and MCP servers give it a broader surface to reason over. Depending on the goal, a workflow could end up mixing all three.