Self-host n8n MCP with Levelrail
A Model Context Protocol server that gives AI assistants searchable n8n node documentation. MIT licensed. The bearer token is generated for you.
- Authorczlonkowski
- LicenceMIT
- Memory256 MiB
- Services1
How to self-host n8n MCP
-
Pull the images
One image is pulled on your server.
Show images
ghcr.io/czlonkowski/n8n-mcp:2.102.0
-
Create the app
One service starts in a single Compose app, on port 3000.
-
Fill in the secrets
1 secret is generated and stored encrypted, 2 settings are preset, you do not have to fill in anything.
-
Open it
Without a domain the app gets an sslip.io address; add --domain SERVICE=HOST to use your own.
After the first start
- Point your MCP client at the public address with the generated token as the bearer token.
n8n MCP requirements
- Memory
- About 256 MiB
- Architectures
- amd64 unknown, arm64 unknown
- Ports
- 3000
- Domain
- Optional, an sslip.io address is used without one
- Settings
- none to fill in
- License
- MIT, permissive license
- Listed. It is in the catalog but not verified. Back up the data volume before changing an image tag.
Install Levelrail first
On a server with Levelrail running, run the command above, or open the dashboard: Apps, New app, Browse templates, then n8n MCP. New to Levelrail? Install it on a fresh VPS first.
docker pull ghcr.io/glincker/levelrail:latest Then levelrail-cli login --device. See Getting started and the n8n MCP docs page.
Deploy n8n MCP your way
Every format below deploys the same pinned images. Pick the one that fits how you work.
Deploy n8n MCP from the CLI
levelrail-cli templates deploy n8n-mcp --name my-n8n-mcp Deploy n8n MCP with the API
curl -X POST -H "Authorization: Bearer $TOKEN" \
https://levelrail.example.com/api/v1/service-templates/n8n-mcp/deploy n8n MCP configuration
n8n MCP services
| Service | Image | Ports | Volumes |
|---|---|---|---|
| n8n-mcp | ghcr.io/czlonkowski/n8n-mcp:2.102.0 | 3000 | none |
n8n MCP environment variables
| Variable | Service | Value |
|---|---|---|
| AUTH_TOKEN | n8n-mcp | Generated at deploy |
| MCP_MODE | n8n-mcp | Preset by the template |
| PORT | n8n-mcp | Preset by the template |
Ports and volumes
- Ports
- 3000
- Volumes
- none
n8n MCP FAQ
How much memory does n8n MCP need?
The catalog lists about 256 MiB of memory for n8n MCP.
Does n8n MCP run on arm64?
For n8n MCP, arm64 support is not confirmed; amd64 is unknown.
What licence is n8n MCP under?
n8n MCP is licensed under MIT, which is permissive, with few conditions on reuse.
Does n8n MCP need configuration before it starts?
No. The template fills in its own defaults and generates secrets at deploy time.
Which ports does n8n MCP use?
n8n MCP listens on port 3000 inside the stack.
Can I deploy n8n MCP on Dokploy or Dokku?
The services and pinned images on this page can be run on any Docker host. The public Dokploy templates list we compared does not have an entry with the same id for n8n MCP, so on Dokploy you would use a Docker Compose application with the file from this page. Dokku deploys container images with its own commands, so the pinned image ghcr.io/czlonkowski/n8n-mcp:2.102.0 is what you deploy there.