Skip to main content
Glama
mastrangi

n8n MCP Server

by mastrangi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
N8N_URLYesYour n8n instance's base URL (e.g. https://n8n.example.com)
N8N_API_KEYYesGenerated from your n8n instance's Settings → API page

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_workflowsA

List n8n workflows, optionally filtered by active status, name, or comma-separated tags.

Defaults to returning up to 100 workflows. n8n caps this at 250 per request; pass a higher limit (up to 250) explicitly if you need more and results seem truncated.

get_workflowA

Get the full definition (nodes, connections, settings) of a workflow by ID.

create_workflowA

Create a new workflow. workflow must include name, nodes, connections, and settings.

To place the workflow in a folder instead of the project root, include parentFolderId (a folder ID from list_folders) in workflow. To create it in a project other than your personal one, include projectId.

update_workflowA

Replace an existing workflow's definition. workflow must include name, nodes, connections, and settings.

delete_workflowB

Delete a workflow by ID.

activate_workflowC

Activate a workflow by ID.

deactivate_workflowC

Deactivate a workflow by ID.

list_executionsA

List workflow executions, optionally filtered by workflow ID or status (success, error, running, waiting).

Defaults to returning up to 100 executions. n8n caps this at 250 per request; pass a higher limit (up to 250) explicitly if you need more and results seem truncated.

get_executionA

Get details of a specific execution by ID. Set include_data=True to include input/output data.

execute_workflowA

Trigger a workflow's execution via its Webhook trigger node, if it has one.

n8n's public API has no generic "run workflow by ID" endpoint, so this only works for workflows containing a Webhook trigger node, and the workflow must be active for the webhook to respond. data, if given, is sent as the JSON request body, landing in the workflow's $json.body.

list_foldersA

List folders within a project, optionally filtered by parent folder or name.

project_id is required — n8n's public API has no way to discover it if your license doesn't support listing projects. If you don't know it, call list_workflows and read shared[0]["projectId"] off any returned workflow.

n8n defaults to returning only 10 folders per page. Pass a higher take (or page through with skip) if a project has more folders than that — results are silently truncated to take with no other signal that more exist.

create_folderA

Create a folder within a project. Pass parent_folder_id to nest it inside another folder instead of the project root.

project_id is required (see list_folders for how to find it), except that n8n also accepts the literal string "personal" to mean your own personal project.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 12 tools

Disambiguation5/5

Each tool targets a distinct resource-action pair: workflow CRUD/lifecycle, execution retrieval/triggering, and folder listing/creation are clearly separated. Even execute_workflow and activate_workflow are unambiguous because their descriptions clarify webhook triggering versus status changes.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern, such as list_workflows, create_folder, and deactivate_workflow. The naming is predictable and makes the action and resource immediately clear.

Tool Count5/5

With 12 tools, the server is well-scoped for managing n8n workflows, executions, and folders. Each tool covers a meaningful operation without redundancy or excessive granularity.

Completeness4/5

Workflow lifecycle coverage is strong: create, read, update, delete, activate, deactivate, and list are all present. Minor gaps exist for folders (no update or delete operations) and executions (no cancel or delete), but core workflows are fully covered and workarounds are available.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources