# How to connect n8n to MCP

[n8n](https://n8n.io/) is a powerful workflow automation tool that lets you build complex automations with a visual node-based interface. It's open-source, self-hostable, and supports hundreds of integrations out of the box.

When combined with [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) servers, n8n can leverage AI agents that have access to your tools and infrastructure, enabling intelligent automation workflows that can interact with your APIs, databases, and other services.

This guide will show you how to connect n8n to a [Gram-hosted MCP server](https://www.speakeasy.com/blog/release-gram-beta) using the example Push Advisor API from the [Gram concepts guide](https://www.speakeasy.com/mcp/core-concepts). You'll learn how to set up the connection, test it, and use natural language to perform vibe checks before running automated deployments.

Find the full code and OpenAPI document in the [Push Advisor API repository](https://github.com/ritza-co/gram-examples/tree/main/push-advisor-api).

## Prerequisites

To follow this tutorial, you need:

- A [Gram account](https://app.getgram.ai)
- [n8n](https://n8n.io/) installed and running (either self-hosted or cloud)
- An API key from an LLM provider supported by n8n (such as Anthropic or OpenAI)

## Creating a Gram MCP server

If you already have a Gram MCP server configured, you can skip to [connecting n8n to your Gram-hosted MCP server](#connecting-n8n-to-your-gram-hosted-mcp-server). For an in-depth guide to how Gram works and more details on how to create a Gram-hosted MCP server, check out the [Gram concepts guide](https://www.speakeasy.com/mcp/core-concepts).

### Setting up a Gram project

In the [Gram dashboard](https://app.getgram.ai), click **New Project** to start the guided setup flow for creating a toolset and MCP server.

![Screenshot of the Gram dashboard showing the New Project link](/assets/docs/gram/img/guides/n8n/gram-new-project.png)

Enter a project name and click **Submit**. 

Gram will then guide you through the following steps.

#### Step 1: Upload the OpenAPI document

Upload the [Push Advisor OpenAPI document](https://github.com/ritza-co/gram-examples/blob/main/push-advisor-api/openapi.yaml), enter the name of your API, and click **Continue**.

![Screenshot of the upload your OpenAPI spec dialog](/assets/docs/gram/img/guides/n8n/upload-openapi-spec.png)

#### Step 2: Create a toolset

Give your toolset a name (for example, `Push Advisor`) and click **Continue**. 

![Screenshot of the create toolset dialog](/assets/docs/gram/img/guides/n8n/create-toolset.png)

Notice that the names of the tools that will be generated from your OpenAPI document are displayed in this dialog.

#### Step 3: Configure MCP

Enter a URL slug for the MCP server and click **Continue**.

![Screenshot of the configure MCP dialog](/assets/docs/gram/img/guides/n8n/configure-mcp.png)

Gram will create the toolset from the OpenAPI document.

Click **Toolsets** in the sidebar to view the Push Advisor toolset.

![Screenshot of the Gram dashboard showing the Push Advisor toolset](/assets/docs/gram/img/guides/n8n/toolset-created.png)

### Configuring environment variables

[Environments](/docs/mcp/secure/environments) store API keys and configuration separate from your toolset logic.

In the **Environments** tab, click the **Default** environment. Click **Edit** and then **Fill for Toolset**. Select the **Push Advisor** toolset and click **Fill Variables** to automatically populate the required variables.

![Screenshot showing the fill for toolset dialog to automatically populate required variables](/assets/docs/gram/img/guides/n8n/fill-env-vars-toolset.png)

The Push Advisor API is hosted at `canpushtoprod.abdulbaaridavids04.workers.dev`, so set the `<API_name>_SERVER_URL` environment variable to `https://canpushtoprod.abdulbaaridavids04.workers.dev`. Click **Update** and then **Save**.

![Set server URL](/assets/docs/gram/img/guides/n8n/set-server-url.png)

### Publishing an MCP server

Let's make the toolset available as an MCP server.

Go to the **MCP** tab, find the Push Advisor toolset, and click **Edit**. 

On the **MCP Details** page, tick the **Public** checkbox and click **Save**.

![Screenshot of the MCP details page](/assets/docs/gram/img/guides/n8n/mcp-details.png)

Scroll down to the **MCP Installation** section and click the **View** button to open the Installation page.

![Screenshot showing the MCP server config dialog for the Push Advisor toolset](/assets/docs/gram/img/guides/n8n/copy-mcp-config.png)

Scroll down to the **Raw Configuration** section and copy the configuration.

![Screenshot showing the raw configuration for the Push Advisor toolset](/assets/docs/gram/img/guides/n8n/copy-raw-config.png)

The configuration will look something like this:

```json
{
  "mcpServers": {
    "GramPushadvisor": {
      "command": "npx",
      "args": [
          "mcp-remote",
          "https://app.getgram.ai/mcp/canipushtoprod"
        ]
    }
  }
}
```

Use the **Authenticated Server** configuration if you want to use the MCP server in a private environment.

You'll need an API key to use an authenticated server. [Generate an API key](/docs/mcp/secure/api-keys) in the **Settings** tab and copy it to the `GRAM_KEY` environment variable in place of `<your-key-here>`.

The authenticated server configuration looks something like this:

```json
{
  "mcpServers": {
    "GramPushadvisor": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://app.getgram.ai/mcp/canipushtoprod",
        "--header",
        "Authorization: ${GRAM_KEY}"
      ],
      "env": {
        "GRAM_KEY": "Bearer <your-key-here>"
      }
    }
  }
}
```

## Connecting n8n to your Gram-hosted MCP server

Now we'll create an n8n workflow that connects to your MCP server.

### Creating a basic workflow

In your n8n instance, create a new workflow. We'll build a simple chat workflow that can interact with the Push Advisor API.

- Add a **Chat Trigger** node to start the workflow:
   - Click the **+** button.
   - Search for `Chat Trigger`.
   - Click anywhere outside the canvas or hit Esc to add the node with default settings.

![Screenshot showing how to add a Chat Trigger node in n8n](/assets/docs/gram/img/guides/n8n/n8n-add-chat-trigger.png)

- Add an **AI Agent** node:
   - Click the **+** button after the Chat Trigger.
   - Search for `AI Agent`.
   - Click anywhere outside the canvas or hit Esc to add the node with default settings.

![Screenshot showing how to add an AI Agent node in n8n](/assets/docs/gram/img/guides/n8n/n8n-add-ai-node.png)

After adding the AI Agent node, you need to configure two things: a chat model and a tool.

### Configuring the chat model

For the chat model, you can use any AI provider you prefer. In this demo, we're using OpenAI:

- Click on the AI Agent node to open its configuration.
- In the **Model** section, select your preferred chat model (for example, OpenAI GPT-4).
- Add your API key for the chosen provider.

![Screenshot showing how to add a chat model in n8n](/assets/docs/gram/img/guides/n8n/n8n-adding-chat-model.png)

### Adding MCP Client Tool

Now add the tool to connect to the Gram MCP server:

- In the **Tools** section, click **Add Tool**.
- Search for `MCP Client` and select it.

![Screenshot showing how to add the MCP Client tool](/assets/docs/gram/img/guides/n8n/n8n-add-mcp-client.png)

- Configure the MCP Client with your Gram server details:
   - Add your public URL from the Gram MCP config: `https://app.getgram.ai/mcp/canipushtoprod`
   - Change the connection type to **HTTP Streamable**

![Screenshot showing the MCP configuration in n8n](/assets/docs/gram/img/guides/n8n/n8n-configure-mcp.png)

### Testing the workflow

Now you should have two connected nodes in your workflow. To test it:

- Click **Open Chat** in the bottom panel.
- Ask a question like, *"Is it safe to push to production today?"*
- The AI agent will use the MCP server to check the current day and provide a response.

![Screenshot showing the final chat interface with a user asking about pushing to production](/assets/docs/gram/img/guides/n8n/n8n-final-output.png)

## Troubleshooting

Let's go through some common issues and how to fix them.

### MCP Client not connecting

If the MCP Client can't connect to your server:

- Verify the server URL is correct.
- Check that the MCP server is published as public in Gram.
- For authenticated servers, ensure your API key is valid.
- Test the connection using the Gram Playground first.

### Tool calls not working

If the AI agent isn't calling the MCP tools:

- Ensure the MCP Client is properly configured in the AI Agent node.
- Check that your AI model has sufficient context about available tools.
- Try being more explicit in your prompts about using the Push Advisor tool.

### Authentication errors

For authenticated servers:

- Verify your Gram API key in the dashboard under **Settings > API Keys**.
- Ensure the authorization header format is correct.
- Check that environment variables are correctly set in Gram.

## What's next

You now have n8n connected to a Gram-hosted MCP server, enabling AI-powered automation workflows with access to your APIs and tools.

Ready to build your own MCP server? [Try Gram today](/book-demo) and see how easy it is to turn any API into agent-ready tools.