*MCP › Connect*

# Connect n8n

> Give an n8n AI Agent Filmo's tools with the MCP Client Tool node.

## Before you start

| What | What the vendor documents |
| --- | --- |
| Plan | Plans: not documented by the vendor. |
| Who adds the connector | Whoever builds the workflow adds the node and its credential. |
| Who connects | Whoever creates the credential; with OAuth, a Filmo administrator consents. |
| Administration | Self-hosted: the base URL of the instance sets the redirect URI. |

verified on 2026-10-09: [MCP Client Tool node](https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolmcp/) · [MCP credentials](https://docs.n8n.io/integrations/builtin/credentials/mcp/)

> **Use exactly this URL:** Type `https://app.filmo.io/api/v1/mcp` exactly. Do not use the Filmo domain of your company or any other host: the OAuth metadata names this origin, and a client that compares it with what you typed rejects a different one.

## Connect with OAuth

1. **Add the node** Add MCP Client Tool to an AI Agent, with the endpoint `https://app.filmo.io/api/v1/mcp`, the Streamable HTTP transport and the MCP OAuth2 credential.
2. **Create the credential** MCP OAuth2 API registers n8n dynamically by default. Copy the OAuth Redirect URL shown in the credential; Filmo accepts any registered redirect, and the consent screen shows its host.
3. **Consent in Filmo** An administrator chooses the subscription and the scopes.

- Self-hosted instances use `<instance base URL>/rest/oauth2-credential/callback`; n8n Cloud shows its own URL in the credential panel.

## The consent screen

- Only the `*:read` scopes the client asked for are checked (every read scope when it asks for none).
- Write scopes, `workflows:run` and `ai:ask` always start unchecked, even if the client asks for them; the ones it asked for carry the label “Requested by the integration”.
- Check by hand only what the assistant needs, and leave `ai:ask` unchecked unless you want it to spend AI credits.

To change the scopes later, remove the connector and add it again.

Before you approve, read [Authentication](https://docs.filmo.io/mcp/authentication#before-you-approve).

## Connect with an API key

1. **Create a Bearer Auth credential** Paste the key as the Bearer token: n8n sends `Authorization: Bearer <token>`. Alternatively use Header Auth with the name `Authorization` and the value `Bearer ` followed by the key.
2. **Choose the tools** Set Tools to Include to Selected and pick only the tools the agent needs.

- The node's documentation page still shows only an SSE endpoint; the node's code defaults to Streamable HTTP from version 1.2.

> **Keep the key out of the repository:** Never paste an API key into a file that goes to version control. The examples read it from the environment or ask for it; if one leaks, revoke it and create another.

## Limits of this client

| What | What the vendor documents |
| --- | --- |
| Tools | Tools to Include: All, Selected, or All Except. |
| Output | A tool output limit: not documented by the vendor. |

## Recommended preset

Availability and schedule (read) (20): `availability:read`, `schedule:read`, `planner:read`, `staff:read`, `vehicles:read`, `items:read`, `spaces:read`, `kits:read`, `account:read`. An agent in a workflow acts without a person: use Selected and a read preset, and add writes only for the tools that need them.

Every preset and its size are in [Limits and context](https://docs.filmo.io/mcp/guides/limits-and-context).

## What to put on “ask before running”

The node has no approval step. Limit the tools with Tools to Include and the key with its scopes.

The tools that must ask for approval are in [Safe writes](https://docs.filmo.io/mcp/guides/safe-writes#requires-confirmation).

## Check the connection

Ask the assistant: “Which Filmo account am I connected to?” It should call `filmo_account_get`, a read tool that returns no personal data.

---

Canonical URL: https://docs.filmo.io/mcp/connect/n8n  
Last updated: 2026-10-25