n8n_fabric

Exposes n8n workflows with semantic search, vector storage, and caching for orchestrated automation across the fabric ecosystem.
  • javascript

0

GitHub Stars

javascript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "ry-ops-n8n-fabric": {
      "command": "uv",
      "args": [
        "run",
        "n8n-fabric-mcp"
      ],
      "env": {
        "N8N_URL": "http://localhost:5678",
        "REDIS_URL": "redis://localhost:6389",
        "QDRANT_URL": "http://localhost:6343",
        "N8N_API_KEY": "YOUR_API_KEY",
        "N8N_ENCRYPTION_KEY": "YOUR_ENCRYPTION_KEY"
      }
    }
  }
}

You run the n8n-fabric MCP Server to expose the n8n workflow engine via a centralized MCP interface, enabling semantic search, vector-backed workflow storage, and fast caching. This server orchestrates access to workflows, executions, credentials, and nodes while coordinating with the broader ry-ops Fabric ecosystem for memory, branding, and repo lifecycle.

How to use

You use an MCP client to connect to the n8n-fabric MCP Server. The MCP surface provides endpoints to list, retrieve, create, update, activate, deactivate, and execute workflows, manage executions and credentials, and query node types. You can perform semantic searches over workflows, recall playbooks and patterns, and coordinate with other fabric components for memory and repository orchestration.

How to install

Prerequisites: ensure you have a compatible runtime environment and the ability to run containerized services or local executables.

Option A: Docker Compose (recommended for quick start)

  1. Install Docker and Docker Compose on your system.

  2. Clone the repository and navigate to the project directory.

  3. Start the full stack in the background. This launches the n8n engine, Qdrant for vectors, Redis for caching, and PostgreSQL for persistent storage.

  4. Access the n8n UI at the indicated URL once services are up.

Commands you run (as separate lines):

docker compose up -d

docker compose ps

open http://localhost:5678

Option B: Local development and MCP run (manual)

If you prefer running the MCP locally for development, follow these steps to start the MCP server process directly.

  1. Install dependencies as required by your local setup.

  2. Set environment variables for the MCP to reach the n8n instance and storage backends.

  3. Start the MCP server process.

Example commands you will run (as separate lines):

uv sync

export N8N_URL=http://localhost:5678
export N8N_API_KEY=your-api-key

uv run n8n-fabric-mcp

Available tools

workflow_list

List all workflows with metadata

workflow_get

Get a workflow by ID (full JSON)

workflow_create

Create a new workflow from JSON

workflow_update

Update an existing workflow

workflow_delete

Delete a workflow

workflow_activate

Activate a workflow

workflow_deactivate

Deactivate a workflow

workflow_execute

Execute a workflow manually

workflow_search

Semantic search across workflows

execution_list

List executions with filters

execution_get

Get execution details and data

execution_delete

Delete an execution

execution_retry

Retry a failed execution

execution_stop

Stop a running execution

credential_list

List credential names (no secrets)

credential_create

Create a new credential

credential_delete

Delete a credential

node_types

List available node types

node_info

Get node type details

n8n_status

n8n health and version

fabric_status

Full stack health check

fabric_sync

Sync workflows to Qdrant

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
n8n_fabric MCP Server - ry-ops/n8n-fabric | VeilStrat